Header logo is ps

85 results (View BibTeX file of all listed publications)

2019

Thumb xl teaser singlecol
Attacking Optical Flow

Ranjan, A., Janai, J., Geiger, A., Black, M. J.

In International Conference on Computer Vision, November 2019 (inproceedings)

Abstract
Deep neural nets achieve state-of-the-art performance on the problem of optical flow estimation. Since optical flow is used in several safety-critical applications like self-driving cars, it is important to gain insights into the robustness of those techniques. Recently, it has been shown that adversarial attacks easily fool deep neural networks to misclassify objects. The robustness of optical flow networks to adversarial attacks, however, has not been studied so far. In this paper, we extend adversarial patch attacks to optical flow networks and show that such attacks can compromise their performance. We show that corrupting a small patch of less than 1% of the image size can significantly affect optical flow estimates. Our attacks lead to noisy flow estimates that extend significantly beyond the region of the attack, in many cases even completely erasing the motion of objects in the scene. While networks using an encoder-decoder architecture are very sensitive to these attacks, we found that networks using a spatial pyramid architecture are less affected. We analyse the success and failure of attacking both architectures by visualizing their feature maps and comparing them to classical optical flow techniques which are robust to these attacks. We also demonstrate that such attacks are practical by placing a printed pattern into real scenes.

Video Project Page Paper Supplementary Material link (url) [BibTex]

2019

Ranjan, A., Janai, J., Geiger, A., Black, M. J. Attacking Optical Flow In International Conference on Computer Vision, November 2019 (inproceedings)

Video Project Page Paper Supplementary Material link (url) [BibTex]

Thumb xl spin3
Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop

Kolotouros, N., Pavlakos, G., Black, M. J., Daniilidis, K.

In International Conference on Computer Vision, October 2019 (inproceedings)

Abstract
Model-based human pose estimation is currently approached through two different paradigms. Optimization-based methods fit a parametric body model to 2D observations in an iterative manner, leading to accurate image-model alignments, but are often slow and sensitive to the initialization. In contrast, regression-based methods, that use a deep network to directly estimate the model parameters from pixels, tend to provide reasonable, but not pixel accurate, results while requiring huge amounts of supervision. In this work, instead of investigating which approach is better, our key insight is that the two paradigms can form a strong collaboration. A reasonable, directly regressed estimate from the network can initialize the iterative optimization making the fitting faster and more accurate. Similarly, a pixel accurate fit from iterative optimization can act as strong supervision for the network. This is the core of our proposed approach SPIN (SMPL oPtimization IN the loop). The deep network initializes an iterative optimization routine that fits the body model to 2D joints within the training loop, and the fitted estimate is subsequently used to supervise the network. Our approach is self-improving by nature, since better network estimates can lead the optimization to better solutions, while more accurate optimization fits provide better supervision for the network. We demonstrate the effectiveness of our approach in different settings, where 3D ground truth is scarce, or not available, and we consistently outperform the state-of-the-art model-based pose estimation approaches by significant margins.

pdf code project [BibTex]

Kolotouros, N., Pavlakos, G., Black, M. J., Daniilidis, K. Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop In International Conference on Computer Vision, October 2019 (inproceedings)

pdf code project [BibTex]

Thumb xl website teaser
Resolving 3D Human Pose Ambiguities with 3D Scene Constraints

Hassan, M., Choutas, V., Tzionas, D., Black, M. J.

In International Conference on Computer Vision, October 2019 (inproceedings)

Abstract
To understand and analyze human behavior, we need to capture humans moving in, and interacting with, the world. Most existing methods perform 3D human pose estimation without explicitly considering the scene. We observe however that the world constrains the body and vice-versa. To motivate this, we show that current 3D human pose estimation methods produce results that are not consistent with the 3D scene. Our key contribution is to exploit static 3D scene structure to better estimate human pose from monocular images. The method enforces Proximal Relationships with Object eXclusion and is called PROX. To test this, we collect a new dataset composed of 12 different 3D scenes and RGB sequences of 20 subjects moving in and interacting with the scenes. We represent human pose using the 3D human body model SMPL-X and extend SMPLify-X to estimate body pose using scene constraints. We make use of the 3D scene information by formulating two main constraints. The interpenetration constraint penalizes intersection between the body model and the surrounding 3D scene. The contact constraint encourages specific parts of the body to be in contact with scene surfaces if they are close enough in distance and orientation. For quantitative evaluation we capture a separate dataset with 180 RGB frames in which the ground-truth body pose is estimated using a motion-capture system. We show quantitatively that introducing scene constraints significantly reduces 3D joint error and vertex error. Our code and data are available for research at https://prox.is.tue.mpg.de.

pdf poster link (url) [BibTex]

Thumb xl end to end learning for graph decomposition
End-to-end Learning for Graph Decomposition

Song, J., Andres, B., Black, M., Hilliges, O., Tang, S.

In International Conference on Computer Vision, October 2019 (inproceedings)

Abstract
Deep neural networks provide powerful tools for pattern recognition, while classical graph algorithms are widely used to solve combinatorial problems. In computer vision, many tasks combine elements of both pattern recognition and graph reasoning. In this paper, we study how to connect deep networks with graph decomposition into an end-to-end trainable framework. More specifically, the minimum cost multicut problem is first converted to an unconstrained binary cubic formulation where cycle consistency constraints are incorporated into the objective function. The new optimization problem can be viewed as a Conditional Random Field (CRF) in which the random variables are associated with the binary edge labels. Cycle constraints are introduced into the CRF as high-order potentials. A standard Convolutional Neural Network (CNN) provides the front-end features for the fully differentiable CRF. The parameters of both parts are optimized in an end-to-end manner. The efficacy of the proposed learning algorithm is demonstrated via experiments on clustering MNIST images and on the challenging task of real-world multi-people pose estimation.

PDF [BibTex]

Song, J., Andres, B., Black, M., Hilliges, O., Tang, S. End-to-end Learning for Graph Decomposition In International Conference on Computer Vision, October 2019 (inproceedings)

PDF [BibTex]

Thumb xl ps web
Three-D Safari: Learning to Estimate Zebra Pose, Shape, and Texture from Images "In the Wild"

Zuffi, S., Kanazawa, A., Berger-Wolf, T., Black, M. J.

In International Conference on Computer Vision, October 2019 (inproceedings)

Abstract
We present the first method to perform automatic 3D pose, shape and texture capture of animals from images acquired in-the-wild. In particular, we focus on the problem of capturing 3D information about Grevy's zebras from a collection of images. The Grevy's zebra is one of the most endangered species in Africa, with only a few thousand individuals left. Capturing the shape and pose of these animals can provide biologists and conservationists with information about animal health and behavior. In contrast to research on human pose, shape and texture estimation, training data for endangered species is limited, the animals are in complex natural scenes with occlusion, they are naturally camouflaged, travel in herds, and look similar to each other. To overcome these challenges, we integrate the recent SMAL animal model into a network-based regression pipeline, which we train end-to-end on synthetically generated images with pose, shape, and background variation. Going beyond state-of-the-art methods for human shape and pose estimation, our method learns a shape space for zebras during training. Learning such a shape space from images using only a photometric loss is novel, and the approach can be used to learn shape in other settings with limited 3D supervision. Moreover, we couple 3D pose and shape prediction with the task of texture synthesis, obtaining a full texture map of the animal from a single image. We show that the predicted texture map allows a novel per-instance unsupervised optimization over the network features. This method, SMALST (SMAL with learned Shape and Texture) goes beyond previous work, which assumed manual keypoints and/or segmentation, to regress directly from pixels to 3D animal shape, pose and texture. Code and data are available at https://github.com/silviazuffi/smalst

code pdf supmat iccv19 presentation Project Page [BibTex]

Thumb xl teaser
Efficient Learning on Point Clouds With Basis Point Sets

Prokudin, S., Lassner, C., Romero, J.

International Conference on Computer Vision, pages: 4332-4341, October 2019 (conference)

Abstract
With an increased availability of 3D scanning technology, point clouds are moving into the focus of computer vision as a rich representation of everyday scenes. However, they are hard to handle for machine learning algorithms due to the unordered structure. One common approach is to apply voxelization, which dramatically increases the amount of data stored and at the same time loses details through discretization. Recently, deep learning models with hand-tailored architectures were proposed to handle point clouds directly and achieve input permutation invariance. However, these architectures use an increased number of parameters and are computationally inefficient. In this work we propose basis point sets as a highly efficient and fully general way to process point clouds with machine learning algorithms. Basis point sets are a residual representation that can be computed efficiently and can be used with standard neural network architectures. Using the proposed representation as the input to a relatively simple network allows us to match the performance of PointNet on a shape classification task while using three order of magnitudes less floating point operations. In a second experiment, we show how proposed representation can be used for obtaining high resolution meshes from noisy 3D scans. Here, our network achieves performance comparable to the state-of-the-art computationally intense multi-step frameworks, in one network pass that can be done in less than 1ms.

[BibTex]

Prokudin, S., Lassner, C., Romero, J. Efficient Learning on Point Clouds With Basis Point Sets International Conference on Computer Vision, pages: 4332-4341, October 2019 (conference)

[BibTex]

Thumb xl iccv 2 cover crop small
Markerless Outdoor Human Motion Capture Using Multiple Autonomous Micro Aerial Vehicles

Saini, N., Price, E., Tallamraju, R., Enficiaud, R., Ludwig, R., Martinović, I., Ahmad, A., Black, M.

In International Conference on Computer Vision, October 2019 (inproceedings) Accepted

Abstract
Capturing human motion in natural scenarios means moving motion capture out of the lab and into the wild. Typical approaches rely on fixed, calibrated, cameras and reflective markers on the body, significantly limiting the motions that can be captured. To make motion capture truly unconstrained, we describe the first fully autonomous outdoor capture system based on flying vehicles. We use multiple micro-aerial-vehicles(MAVs), each equipped with a monocular RGB camera, an IMU, and a GPS receiver module. These detect the person, optimize their position, and localize themselves approximately. We then develop a markerless motion capture method that is suitable for this challenging scenario with a distant subject, viewed from above, with approximately calibrated and moving cameras. We combine multiple state-of-the-art 2D joint detectors with a 3D human body model and a powerful prior on human pose. We jointly optimize for 3D body pose and camera pose to robustly fit the 2D measurements. To our knowledge, this is the first successful demonstration of outdoor, full-body, markerless motion capture from autonomous flying vehicles.

Code Data Video Paper Manuscript Project Page [BibTex]

Thumb xl amass
AMASS: Archive of Motion Capture as Surface Shapes

Mahmood, N., Ghorbani, N., Troje, N. F., Pons-Moll, G., Black, M. J.

International Conference on Computer Vision, October 2019 (conference)

Abstract
Large datasets are the cornerstone of recent advances in computer vision using deep learning. In contrast, existing human motion capture (mocap) datasets are small and the motions limited, hampering progress on learning models of human motion. While there are many different datasets available, they each use a different parameterization of the body, making it difficult to integrate them into a single meta dataset. To address this, we introduce AMASS, a large and varied database of human motion that unifies 15 different optical marker-based mocap datasets by representing them within a common framework and parameterization. We achieve this using a new method, MoSh++, that converts mocap data into realistic 3D human meshes represented by a rigged body model. Here we use SMPL [26], which is widely used and provides a standard skeletal representation as well as a fully rigged surface mesh. The method works for arbitrary marker-sets, while recovering soft-tissue dynamics and realistic hand motion. We evaluate MoSh++ and tune its hyper-parameters using a new dataset of 4D body scans that are jointly recorded with marker-based mocap. The consistent representation of AMASS makes it readily useful for animation, visualization, and generating training data for deep learning. Our dataset is significantly richer than previous human motion collections, having more than 40 hours of motion data, spanning over 300 subjects, more than 11000 motions, and is available for research at https://amass.is.tue.mpg.de/.

code pdf suppl arxiv project website video poster AMASS_Poster [BibTex]

Thumb xl lala2
Learning to Train with Synthetic Humans

Hoffmann, D. T., Tzionas, D., Black, M. J., Tang, S.

In German Conference on Pattern Recognition (GCPR), September 2019 (inproceedings)

Abstract
Neural networks need big annotated datasets for training. However, manual annotation can be too expensive or even unfeasible for certain tasks, like multi-person 2D pose estimation with severe occlusions. A remedy for this is synthetic data with perfect ground truth. Here we explore two variations of synthetic data for this challenging problem; a dataset with purely synthetic humans, as well as a real dataset augmented with synthetic humans. We then study which approach better generalizes to real data, as well as the influence of virtual humans in the training loss. We observe that not all synthetic samples are equally informative for training, while the informative samples are different for each training stage. To exploit this observation, we employ an adversarial student-teacher framework; the teacher improves the student by providing the hardest samples for its current state as a challenge. Experiments show that this student-teacher framework outperforms all our baselines.

pdf suppl poster link (url) [BibTex]

Hoffmann, D. T., Tzionas, D., Black, M. J., Tang, S. Learning to Train with Synthetic Humans In German Conference on Pattern Recognition (GCPR), September 2019 (inproceedings)

pdf suppl poster link (url) [BibTex]

Thumb xl sap
The Influence of Visual Perspective on Body Size Estimation in Immersive Virtual Reality

Thaler, A., Pujades, S., Stefanucci, J. K., Creem-Regehr, S. H., Tesch, J., Black, M. J., Mohler, B. J.

In ACM Symposium on Applied Perception, September 2019 (inproceedings)

Abstract
The creation of realistic self-avatars that users identify with is important for many virtual reality applications. However, current approaches for creating biometrically plausible avatars that represent a particular individual require expertise and are time-consuming. We investigated the visual perception of an avatar’s body dimensions by asking males and females to estimate their own body weight and shape on a virtual body using a virtual reality avatar creation tool. In a method of adjustment task, the virtual body was presented in an HTC Vive head-mounted display either co-located with (first-person perspective) or facing (third-person perspective) the participants. Participants adjusted the body weight and dimensions of various body parts to match their own body shape and size. Both males and females underestimated their weight by 10-20% in the virtual body, but the estimates of the other body dimensions were relatively accurate and within a range of ±6%. There was a stronger influence of visual perspective on the estimates for males, but this effect was dependent on the amount of control over the shape of the virtual body, indicating that the results might be caused by where in the body the weight changes expressed themselves. These results suggest that this avatar creation tool could be used to allow participants to make a relatively accurate self-avatar in terms of adjusting body part dimensions, but not weight, and that the influence of visual perspective and amount of control needed over the body shape are likely gender-specific.

pdf [BibTex]

Thaler, A., Pujades, S., Stefanucci, J. K., Creem-Regehr, S. H., Tesch, J., Black, M. J., Mohler, B. J. The Influence of Visual Perspective on Body Size Estimation in Immersive Virtual Reality In ACM Symposium on Applied Perception, September 2019 (inproceedings)

pdf [BibTex]

Thumb xl cover
Motion Planning for Multi-Mobile-Manipulator Payload Transport Systems

Tallamraju, R., Salunkhe, D., Rajappa, S., Ahmad, A., Karlapalem, K., Shah, S. V.

In 15th IEEE International Conference on Automation Science and Engineering, IEEE, August 2019 (inproceedings) Accepted

[BibTex]

Tallamraju, R., Salunkhe, D., Rajappa, S., Ahmad, A., Karlapalem, K., Shah, S. V. Motion Planning for Multi-Mobile-Manipulator Payload Transport Systems In 15th IEEE International Conference on Automation Science and Engineering, IEEE, August 2019 (inproceedings) Accepted

[BibTex]

Thumb xl teaser results
Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation

Ranjan, A., Jampani, V., Balles, L., Kim, K., Sun, D., Wulff, J., Black, M. J.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2019 (inproceedings)

Abstract
We address the unsupervised learning of several interconnected problems in low-level vision: single view depth prediction, camera motion estimation, optical flow, and segmentation of a video into the static scene and moving regions. Our key insight is that these four fundamental vision problems are coupled through geometric constraints. Consequently, learning to solve them together simplifies the problem because the solutions can reinforce each other. We go beyond previous work by exploiting geometry more explicitly and segmenting the scene into static and moving regions. To that end, we introduce Competitive Collaboration, a framework that facilitates the coordinated training of multiple specialized neural networks to solve complex problems. Competitive Collaboration works much like expectation-maximization, but with neural networks that act as both competitors to explain pixels that correspond to static or moving regions, and as collaborators through a moderator that assigns pixels to be either static or independently moving. Our novel method integrates all these problems in a common framework and simultaneously reasons about the segmentation of the scene into moving objects and the static background, the camera motion, depth of the static scene structure, and the optical flow of moving objects. Our model is trained without any supervision and achieves state-of-the-art performance among joint unsupervised methods on all sub-problems.

Paper link (url) Project Page Project Page [BibTex]

Thumb xl cvpr2019 demo v2.001
Local Temporal Bilinear Pooling for Fine-grained Action Parsing

Zhang, Y., Tang, S., Muandet, K., Jarvers, C., Neumann, H.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2019 (inproceedings)

Abstract
Fine-grained temporal action parsing is important in many applications, such as daily activity understanding, human motion analysis, surgical robotics and others requiring subtle and precise operations in a long-term period. In this paper we propose a novel bilinear pooling operation, which is used in intermediate layers of a temporal convolutional encoder-decoder net. In contrast to other work, our proposed bilinear pooling is learnable and hence can capture more complex local statistics than the conventional counterpart. In addition, we introduce exact lower-dimension representations of our bilinear forms, so that the dimensionality is reduced with neither information loss nor extra computation. We perform intensive experiments to quantitatively analyze our model and show the superior performances to other state-of-the-art work on various datasets.

Code video demo pdf link (url) [BibTex]

Zhang, Y., Tang, S., Muandet, K., Jarvers, C., Neumann, H. Local Temporal Bilinear Pooling for Fine-grained Action Parsing In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2019 (inproceedings)

Code video demo pdf link (url) [BibTex]

Thumb xl ringnet
Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision

Sanyal, S., Bolkart, T., Feng, H., Black, M. J.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2019 (inproceedings)

Abstract
The estimation of 3D face shape from a single image must be robust to variations in lighting, head pose, expression, facial hair, makeup, and occlusions. Robustness requires a large training set of in-the-wild images, which by construction, lack ground truth 3D shape. To train a network without any 2D-to-3D supervision, we present RingNet, which learns to compute 3D face shape from a single image. Our key observation is that an individual’s face shape is constant across images, regardless of expression, pose, lighting, etc. RingNet leverages multiple images of a person and automatically detected 2D face features. It uses a novel loss that encourages the face shape to be similar when the identity is the same and different for different people. We achieve invariance to expression by representing the face using the FLAME model. Once trained, our method takes a single image and outputs the parameters of FLAME, which can be readily animated. Additionally we create a new database of faces “not quite in-the-wild” (NoW) with 3D head scans and high-resolution images of the subjects in a wide variety of conditions. We evaluate publicly available methods and find that RingNet is more accurate than methods that use 3D supervision. The dataset, model, and results are available for research purposes.

code pdf preprint link (url) Project Page [BibTex]

Thumb xl obman new
Learning Joint Reconstruction of Hands and Manipulated Objects

Hasson, Y., Varol, G., Tzionas, D., Kalevatykh, I., Black, M. J., Laptev, I., Schmid, C.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2019 (inproceedings)

Abstract
Estimating hand-object manipulations is essential for interpreting and imitating human actions. Previous work has made significant progress towards reconstruction of hand poses and object shapes in isolation. Yet, reconstructing hands and objects during manipulation is a more challenging task due to significant occlusions of both the hand and object. While presenting challenges, manipulations may also simplify the problem since the physics of contact restricts the space of valid hand-object configurations. For example, during manipulation, the hand and object should be in contact but not interpenetrate. In this work, we regularize the joint reconstruction of hands and objects with manipulation constraints. We present an end-to-end learnable model that exploits a novel contact loss that favors physically plausible hand-object constellations. Our approach improves grasp quality metrics over baselines, using RGB images as input. To train and evaluate the model, we also propose a new large-scale synthetic dataset, ObMan, with hand-object manipulations. We demonstrate the transferability of ObMan-trained models to real data.

pdf suppl poster link (url) Project Page Project Page [BibTex]

Hasson, Y., Varol, G., Tzionas, D., Kalevatykh, I., Black, M. J., Laptev, I., Schmid, C. Learning Joint Reconstruction of Hands and Manipulated Objects In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2019 (inproceedings)

pdf suppl poster link (url) Project Page Project Page [BibTex]

Thumb xl smplx teaser watermark
Expressive Body Capture: 3D Hands, Face, and Body from a Single Image

Pavlakos, G., Choutas, V., Ghorbani, N., Bolkart, T., Osman, A. A. A., Tzionas, D., Black, M. J.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2019 (inproceedings)

Abstract
To facilitate the analysis of human actions, interactions and emotions, we compute a 3D model of human body pose, hand pose, and facial expression from a single monocular image. To achieve this, we use thousands of 3D scans to train a new, unified, 3D model of the human body, SMPL-X, that extends SMPL with fully articulated hands and an expressive face. Learning to regress the parameters of SMPL-X directly from images is challenging without paired images and 3D ground truth. Consequently, we follow the approach of SMPLify, which estimates 2D features and then optimizes model parameters to fit the features. We improve on SMPLify in several significant ways: (1) we detect 2D features corresponding to the face, hands, and feet and fit the full SMPL-X model to these; (2) we train a new neural network pose prior using a large MoCap dataset; (3) we define a new interpenetration penalty that is both fast and accurate; (4) we automatically detect gender and the appropriate body models (male, female, or neutral); (5) our PyTorch implementation achieves a speedup of more than 8x over Chumpy. We use the new method, SMPLify-X, to fit SMPL-X to both controlled images and images in the wild. We evaluate 3D accuracy on a new curated dataset comprising 100 images with pseudo ground-truth. This is a step towards automatic expressive human capture from monocular RGB data. The models, code, and data are available for research purposes at https://smpl-x.is.tue.mpg.de.

video code pdf suppl poster link (url) Project Page [BibTex]

Thumb xl voca
Capture, Learning, and Synthesis of 3D Speaking Styles

Cudeiro, D., Bolkart, T., Laidlaw, C., Ranjan, A., Black, M. J.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2019 (inproceedings)

Abstract
Audio-driven 3D facial animation has been widely explored, but achieving realistic, human-like performance is still unsolved. This is due to the lack of available 3D datasets, models, and standard evaluation metrics. To address this, we introduce a unique 4D face dataset with about 29 minutes of 4D scans captured at 60 fps and synchronized audio from 12 speakers. We then train a neural network on our dataset that factors identity from facial motion. The learned model, VOCA (Voice Operated Character Animation) takes any speech signal as input—even speech in languages other than English—and realistically animates a wide range of adult faces. Conditioning on subject labels during training allows the model to learn a variety of realistic speaking styles. VOCA also provides animator controls to alter speaking style, identity-dependent facial shape, and pose (i.e. head, jaw, and eyeball rotations) during animation. To our knowledge, VOCA is the only realistic 3D facial animation model that is readily applicable to unseen subjects without retargeting. This makes VOCA suitable for tasks like in-game video, virtual reality avatars, or any scenario in which the speaker, speech, or language is not known in advance. We make the dataset and model available for research purposes at http://voca.is.tue.mpg.de.

code Project Page video paper [BibTex]

Cudeiro, D., Bolkart, T., Laidlaw, C., Ranjan, A., Black, M. J. Capture, Learning, and Synthesis of 3D Speaking Styles In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2019 (inproceedings)

code Project Page video paper [BibTex]

Thumb xl model
Resisting Adversarial Attacks using Gaussian Mixture Variational Autoencoders

Ghosh, P., Losalka, A., Black, M. J.

In Proc. AAAI, 2019 (inproceedings)

Abstract
Susceptibility of deep neural networks to adversarial attacks poses a major theoretical and practical challenge. All efforts to harden classifiers against such attacks have seen limited success till now. Two distinct categories of samples against which deep neural networks are vulnerable, ``adversarial samples" and ``fooling samples", have been tackled separately so far due to the difficulty posed when considered together. In this work, we show how one can defend against them both under a unified framework. Our model has the form of a variational autoencoder with a Gaussian mixture prior on the latent variable, such that each mixture component corresponds to a single class. We show how selective classification can be performed using this model, thereby causing the adversarial objective to entail a conflict. The proposed method leads to the rejection of adversarial samples instead of misclassification, while maintaining high precision and recall on test data. It also inherently provides a way of learning a selective classifier in a semi-supervised scenario, which can similarly resist adversarial attacks. We further show how one can reclassify the detected adversarial samples by iterative optimization.

link (url) Project Page [BibTex]

Thumb xl rae
From Variational to Deterministic Autoencoders

Ghosh*, P., Sajjadi*, M. S. M., Vergari, A., Black, M. J., Schölkopf, B.

2019, *equal contribution (conference) Submitted

Abstract
Variational Autoencoders (VAEs) provide a theoretically-backed framework for deep generative models. However, they often produce “blurry” images, which is linked to their training objective. Sampling in the most popular implementation, the Gaussian VAE, can be interpreted as simply injecting noise to the input of a deterministic decoder. In practice, this simply enforces a smooth latent space structure. We challenge the adoption of the full VAE framework on this specific point in favor of a simpler, deterministic one. Specifically, we investigate how substituting stochasticity with other explicit and implicit regularization schemes can lead to a meaningful latent space without having to force it to conform to an arbitrarily chosen prior. To retrieve a generative mechanism for sampling new data points, we propose to employ an efficient ex-post density estimation step that can be readily adopted both for the proposed deterministic autoencoders as well as to improve sample quality of existing VAEs. We show in a rigorous empirical study that regularized deterministic autoencoding achieves state-of-the-art sample quality on the common MNIST, CIFAR-10 and CelebA datasets.

arXiv [BibTex]

2017

Thumb xl teasercrop
A Generative Model of People in Clothing

Lassner, C., Pons-Moll, G., Gehler, P. V.

In Proceedings IEEE International Conference on Computer Vision (ICCV), IEEE, Piscataway, NJ, USA, October 2017 (inproceedings)

Abstract
We present the first image-based generative model of people in clothing in a full-body setting. We sidestep the commonly used complex graphics rendering pipeline and the need for high-quality 3D scans of dressed people. Instead, we learn generative models from a large image database. The main challenge is to cope with the high variance in human pose, shape and appearance. For this reason, pure image-based approaches have not been considered so far. We show that this challenge can be overcome by splitting the generating process in two parts. First, we learn to generate a semantic segmentation of the body and clothing. Second, we learn a conditional model on the resulting segments that creates realistic images. The full model is differentiable and can be conditioned on pose, shape or color. The result are samples of people in different clothing items and styles. The proposed model can generate entirely new people with realistic clothing. In several experiments we present encouraging results that suggest an entirely data-driven approach to people generation is possible.

link (url) Project Page [BibTex]

2017

Lassner, C., Pons-Moll, G., Gehler, P. V. A Generative Model of People in Clothing In Proceedings IEEE International Conference on Computer Vision (ICCV), IEEE, Piscataway, NJ, USA, October 2017 (inproceedings)

link (url) Project Page [BibTex]

Thumb xl website teaser
Semantic Video CNNs through Representation Warping

Gadde, R., Jampani, V., Gehler, P. V.

In Proceedings IEEE International Conference on Computer Vision (ICCV), IEEE, Piscataway, NJ, USA, October 2017 (inproceedings) Accepted

Abstract
In this work, we propose a technique to convert CNN models for semantic segmentation of static images into CNNs for video data. We describe a warping method that can be used to augment existing architectures with very lit- tle extra computational cost. This module is called Net- Warp and we demonstrate its use for a range of network architectures. The main design principle is to use optical flow of adjacent frames for warping internal network repre- sentations across time. A key insight of this work is that fast optical flow methods can be combined with many different CNN architectures for improved performance and end-to- end training. Experiments validate that the proposed ap- proach incurs only little extra computational cost, while im- proving performance, when video streams are available. We achieve new state-of-the-art results on the standard CamVid and Cityscapes benchmark datasets and show reliable im- provements over different baseline networks. Our code and models are available at http://segmentation.is. tue.mpg.de

pdf Supplementary Project Page [BibTex]

Gadde, R., Jampani, V., Gehler, P. V. Semantic Video CNNs through Representation Warping In Proceedings IEEE International Conference on Computer Vision (ICCV), IEEE, Piscataway, NJ, USA, October 2017 (inproceedings) Accepted

pdf Supplementary Project Page [BibTex]

Thumb xl screen shot 2017 08 09 at 12.54.00
A simple yet effective baseline for 3d human pose estimation

Martinez, J., Hossain, R., Romero, J., Little, J. J.

In Proceedings IEEE International Conference on Computer Vision (ICCV), IEEE, Piscataway, NJ, USA, October 2017 (inproceedings)

Abstract
Following the success of deep convolutional networks, state-of-the-art methods for 3d human pose estimation have focused on deep end-to-end systems that predict 3d joint locations given raw image pixels. Despite their excellent performance, it is often not easy to understand whether their remaining error stems from a limited 2d pose (visual) understanding, or from a failure to map 2d poses into 3-dimensional positions. With the goal of understanding these sources of error, we set out to build a system that given 2d joint locations predicts 3d positions. Much to our surprise, we have found that, with current technology, "lifting" ground truth 2d joint locations to 3d space is a task that can be solved with a remarkably low error rate: a relatively simple deep feed-forward network outperforms the best reported result by about 30\% on Human3.6M, the largest publicly available 3d pose estimation benchmark. Furthermore, training our system on the output of an off-the-shelf state-of-the-art 2d detector (\ie, using images as input) yields state of the art results -- this includes an array of systems that have been trained end-to-end specifically for this task. Our results indicate that a large portion of the error of modern deep 3d pose estimation systems stems from their visual analysis, and suggests directions to further advance the state of the art in 3d human pose estimation.

video code arxiv pdf preprint Project Page [BibTex]

Martinez, J., Hossain, R., Romero, J., Little, J. J. A simple yet effective baseline for 3d human pose estimation In Proceedings IEEE International Conference on Computer Vision (ICCV), IEEE, Piscataway, NJ, USA, October 2017 (inproceedings)

video code arxiv pdf preprint Project Page [BibTex]

Thumb xl kenny
Effects of animation retargeting on perceived action outcomes

Kenny, S., Mahmood, N., Honda, C., Black, M. J., Troje, N. F.

Proceedings of the ACM Symposium on Applied Perception (SAP’17), pages: 2:1-2:7, September 2017 (conference)

Abstract
The individual shape of the human body, including the geometry of its articulated structure and the distribution of weight over that structure, influences the kinematics of a person's movements. How sensitive is the visual system to inconsistencies between shape and motion introduced by retargeting motion from one person onto the shape of another? We used optical motion capture to record five pairs of male performers with large differences in body weight, while they pushed, lifted, and threw objects. Based on a set of 67 markers, we estimated both the kinematics of the actions as well as the performer's individual body shape. To obtain consistent and inconsistent stimuli, we created animated avatars by combining the shape and motion estimates from either a single performer or from different performers. In a virtual reality environment, observers rated the perceived weight or thrown distance of the objects. They were also asked to explicitly discriminate between consistent and hybrid stimuli. Observers were unable to accomplish the latter, but hybridization of shape and motion influenced their judgements of action outcome in systematic ways. Inconsistencies between shape and motion were assimilated into an altered perception of the action outcome.

pdf DOI [BibTex]

Kenny, S., Mahmood, N., Honda, C., Black, M. J., Troje, N. F. Effects of animation retargeting on perceived action outcomes Proceedings of the ACM Symposium on Applied Perception (SAP’17), pages: 2:1-2:7, September 2017 (conference)

pdf DOI [BibTex]

Thumb xl teaser
Coupling Adaptive Batch Sizes with Learning Rates

Balles, L., Romero, J., Hennig, P.

In Proceedings Conference on Uncertainty in Artificial Intelligence (UAI) 2017, pages: 410-419, (Editors: Gal Elidan and Kristian Kersting), Association for Uncertainty in Artificial Intelligence (AUAI), August 2017 (inproceedings)

Abstract
Mini-batch stochastic gradient descent and variants thereof have become standard for large-scale empirical risk minimization like the training of neural networks. These methods are usually used with a constant batch size chosen by simple empirical inspection. The batch size significantly influences the behavior of the stochastic optimization algorithm, though, since it determines the variance of the gradient estimates. This variance also changes over the optimization process; when using a constant batch size, stability and convergence is thus often enforced by means of a (manually tuned) decreasing learning rate schedule. We propose a practical method for dynamic batch size adaptation. It estimates the variance of the stochastic gradients and adapts the batch size to decrease the variance proportionally to the value of the objective function, removing the need for the aforementioned learning rate decrease. In contrast to recent related work, our algorithm couples the batch size to the learning rate, directly reflecting the known relationship between the two. On three image classification benchmarks, our batch size adaptation yields faster optimization convergence, while simultaneously simplifying learning rate tuning. A TensorFlow implementation is available.

Code link (url) Project Page [BibTex]

Balles, L., Romero, J., Hennig, P. Coupling Adaptive Batch Sizes with Learning Rates In Proceedings Conference on Uncertainty in Artificial Intelligence (UAI) 2017, pages: 410-419, (Editors: Gal Elidan and Kristian Kersting), Association for Uncertainty in Artificial Intelligence (AUAI), August 2017 (inproceedings)

Code link (url) Project Page [BibTex]

Thumb xl 1611.04399 image
Joint Graph Decomposition and Node Labeling by Local Search

Levinkov, E., Uhrig, J., Tang, S., Omran, M., Insafutdinov, E., Kirillov, A., Rother, C., Brox, T., Schiele, B., Andres, B.

In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 1904-1912, IEEE, July 2017 (inproceedings)

PDF Supplementary DOI Project Page [BibTex]

Levinkov, E., Uhrig, J., Tang, S., Omran, M., Insafutdinov, E., Kirillov, A., Rother, C., Brox, T., Schiele, B., Andres, B. Joint Graph Decomposition and Node Labeling by Local Search In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 1904-1912, IEEE, July 2017 (inproceedings)

PDF Supplementary DOI Project Page [BibTex]

Thumb xl teaser
Dynamic FAUST: Registering Human Bodies in Motion

Bogo, F., Romero, J., Pons-Moll, G., Black, M. J.

In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

Abstract
While the ready availability of 3D scan data has influenced research throughout computer vision, less attention has focused on 4D data; that is 3D scans of moving nonrigid objects, captured over time. To be useful for vision research, such 4D scans need to be registered, or aligned, to a common topology. Consequently, extending mesh registration methods to 4D is important. Unfortunately, no ground-truth datasets are available for quantitative evaluation and comparison of 4D registration methods. To address this we create a novel dataset of high-resolution 4D scans of human subjects in motion, captured at 60 fps. We propose a new mesh registration method that uses both 3D geometry and texture information to register all scans in a sequence to a common reference topology. The approach exploits consistency in texture over both short and long time intervals and deals with temporal offsets between shape and texture capture. We show how using geometry alone results in significant errors in alignment when the motions are fast and non-rigid. We evaluate the accuracy of our registration and provide a dataset of 40,000 raw and aligned meshes. Dynamic FAUST extends the popular FAUST dataset to dynamic 4D data, and is available for research purposes at http://dfaust.is.tue.mpg.de.

pdf video Project Page Project Page Project Page [BibTex]

Bogo, F., Romero, J., Pons-Moll, G., Black, M. J. Dynamic FAUST: Registering Human Bodies in Motion In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

pdf video Project Page Project Page Project Page [BibTex]

Thumb xl surrealin
Learning from Synthetic Humans

Varol, G., Romero, J., Martin, X., Mahmood, N., Black, M. J., Laptev, I., Schmid, C.

In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

Abstract
Estimating human pose, shape, and motion from images and videos are fundamental challenges with many applications. Recent advances in 2D human pose estimation use large amounts of manually-labeled training data for learning convolutional neural networks (CNNs). Such data is time consuming to acquire and difficult to extend. Moreover, manual labeling of 3D pose, depth and motion is impractical. In this work we present SURREAL (Synthetic hUmans foR REAL tasks): a new large-scale dataset with synthetically-generated but realistic images of people rendered from 3D sequences of human motion capture data. We generate more than 6 million frames together with ground truth pose, depth maps, and segmentation masks. We show that CNNs trained on our synthetic dataset allow for accurate human depth estimation and human part segmentation in real RGB images. Our results and the new dataset open up new possibilities for advancing person analysis using cheap and large-scale synthetic data.

arXiv project data Project Page Project Page [BibTex]

Varol, G., Romero, J., Martin, X., Mahmood, N., Black, M. J., Laptev, I., Schmid, C. Learning from Synthetic Humans In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

arXiv project data Project Page Project Page [BibTex]

Thumb xl martinez
On human motion prediction using recurrent neural networks

Martinez, J., Black, M. J., Romero, J.

In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

Abstract
Human motion modelling is a classical problem at the intersection of graphics and computer vision, with applications spanning human-computer interaction, motion synthesis, and motion prediction for virtual and augmented reality. Following the success of deep learning methods in several computer vision tasks, recent work has focused on using deep recurrent neural networks (RNNs) to model human motion, with the goal of learning time-dependent representations that perform tasks such as short-term motion prediction and long-term human motion synthesis. We examine recent work, with a focus on the evaluation methodologies commonly used in the literature, and show that, surprisingly, state-of-the-art performance can be achieved by a simple baseline that does not attempt to model motion at all. We investigate this result, and analyze recent RNN methods by looking at the architectures, loss functions, and training procedures used in state-of-the-art approaches. We propose three changes to the standard RNN models typically used for human motion, which result in a simple and scalable RNN architecture that obtains state-of-the-art performance on human motion prediction.

arXiv Project Page [BibTex]

Martinez, J., Black, M. J., Romero, J. On human motion prediction using recurrent neural networks In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

arXiv Project Page [BibTex]

Thumb xl untitled
Articulated Multi-person Tracking in the Wild

Insafutdinov, E., Andriluka, M., Pishchulin, L., Tang, S., Levinkov, E., Andres, B., Schiele, B.

In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 1293-1301, IEEE, July 2017, Oral (inproceedings)

DOI [BibTex]

Insafutdinov, E., Andriluka, M., Pishchulin, L., Tang, S., Levinkov, E., Andres, B., Schiele, B. Articulated Multi-person Tracking in the Wild In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 1293-1301, IEEE, July 2017, Oral (inproceedings)

DOI [BibTex]

Thumb xl joel slow flow crop
Slow Flow: Exploiting High-Speed Cameras for Accurate and Diverse Optical Flow Reference Data

Janai, J., Güney, F., Wulff, J., Black, M., Geiger, A.

In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, pages: 1406-1416, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

Abstract
Existing optical flow datasets are limited in size and variability due to the difficulty of capturing dense ground truth. In this paper, we tackle this problem by tracking pixels through densely sampled space-time volumes recorded with a high-speed video camera. Our model exploits the linearity of small motions and reasons about occlusions from multiple frames. Using our technique, we are able to establish accurate reference flow fields outside the laboratory in natural environments. Besides, we show how our predictions can be used to augment the input images with realistic motion blur. We demonstrate the quality of the produced flow fields on synthetic and real-world datasets. Finally, we collect a novel challenging optical flow dataset by applying our technique on data from a high-speed camera and analyze the performance of the state-of-the-art in optical flow under various levels of motion blur.

pdf suppmat Project page Video DOI Project Page [BibTex]

Janai, J., Güney, F., Wulff, J., Black, M., Geiger, A. Slow Flow: Exploiting High-Speed Cameras for Accurate and Diverse Optical Flow Reference Data In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, pages: 1406-1416, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

pdf suppmat Project page Video DOI Project Page [BibTex]

Thumb xl mrflow
Optical Flow in Mostly Rigid Scenes

Wulff, J., Sevilla-Lara, L., Black, M. J.

In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, pages: 6911-6920, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

Abstract
The optical flow of natural scenes is a combination of the motion of the observer and the independent motion of objects. Existing algorithms typically focus on either recovering motion and structure under the assumption of a purely static world or optical flow for general unconstrained scenes. We combine these approaches in an optical flow algorithm that estimates an explicit segmentation of moving objects from appearance and physical constraints. In static regions we take advantage of strong constraints to jointly estimate the camera motion and the 3D structure of the scene over multiple frames. This allows us to also regularize the structure instead of the motion. Our formulation uses a Plane+Parallax framework, which works even under small baselines, and reduces the motion estimation to a one-dimensional search problem, resulting in more accurate estimation. In moving regions the flow is treated as unconstrained, and computed with an existing optical flow method. The resulting Mostly-Rigid Flow (MR-Flow) method achieves state-of-the-art results on both the MPISintel and KITTI-2015 benchmarks.

pdf SupMat video code Project Page [BibTex]

Wulff, J., Sevilla-Lara, L., Black, M. J. Optical Flow in Mostly Rigid Scenes In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, pages: 6911-6920, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

pdf SupMat video code Project Page [BibTex]

Thumb xl img03
OctNet: Learning Deep 3D Representations at High Resolutions

Riegler, G., Ulusoy, O., Geiger, A.

In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

Abstract
We present OctNet, a representation for deep learning with sparse 3D data. In contrast to existing models, our representation enables 3D convolutional networks which are both deep and high resolution. Towards this goal, we exploit the sparsity in the input data to hierarchically partition the space using a set of unbalanced octrees where each leaf node stores a pooled feature representation. This allows to focus memory allocation and computation to the relevant dense regions and enables deeper networks without compromising resolution. We demonstrate the utility of our OctNet representation by analyzing the impact of resolution on several 3D tasks including 3D object classification, orientation estimation and point cloud labeling.

pdf suppmat Project Page Video Project Page [BibTex]

Riegler, G., Ulusoy, O., Geiger, A. OctNet: Learning Deep 3D Representations at High Resolutions In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

pdf suppmat Project Page Video Project Page [BibTex]

Thumb xl 71341 r guided
Reflectance Adaptive Filtering Improves Intrinsic Image Estimation

Nestmeyer, T., Gehler, P. V.

In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 1771-1780, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

pre-print DOI Project Page Project Page [BibTex]

Nestmeyer, T., Gehler, P. V. Reflectance Adaptive Filtering Improves Intrinsic Image Estimation In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 1771-1780, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

pre-print DOI Project Page Project Page [BibTex]

Thumb xl web teaser
Detailed, accurate, human shape estimation from clothed 3D scan sequences

Zhang, C., Pujades, S., Black, M., Pons-Moll, G.

In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, Washington, DC, USA, July 2017, Spotlight (inproceedings)

Abstract
We address the problem of estimating human body shape from 3D scans over time. Reliable estimation of 3D body shape is necessary for many applications including virtual try-on, health monitoring, and avatar creation for virtual reality. Scanning bodies in minimal clothing, however, presents a practical barrier to these applications. We address this problem by estimating body shape under clothing from a sequence of 3D scans. Previous methods that have exploited statistical models of body shape produce overly smooth shapes lacking personalized details. In this paper we contribute a new approach to recover not only an approximate shape of the person, but also their detailed shape. Our approach allows the estimated shape to deviate from a parametric model to fit the 3D scans. We demonstrate the method using high quality 4D data as well as sequences of visual hulls extracted from multi-view images. We also make available a new high quality 4D dataset that enables quantitative evaluation. Our method outperforms the previous state of the art, both qualitatively and quantitatively.

arxiv_preprint video dataset pdf supplemental DOI Project Page [BibTex]

Zhang, C., Pujades, S., Black, M., Pons-Moll, G. Detailed, accurate, human shape estimation from clothed 3D scan sequences In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, Washington, DC, USA, July 2017, Spotlight (inproceedings)

arxiv_preprint video dataset pdf supplemental DOI Project Page [BibTex]

Thumb xl slide1
3D Menagerie: Modeling the 3D Shape and Pose of Animals

Zuffi, S., Kanazawa, A., Jacobs, D., Black, M. J.

In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, pages: 5524-5532, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

Abstract
There has been significant work on learning realistic, articulated, 3D models of the human body. In contrast, there are few such models of animals, despite many applications. The main challenge is that animals are much less cooperative than humans. The best human body models are learned from thousands of 3D scans of people in specific poses, which is infeasible with live animals. Consequently, we learn our model from a small set of 3D scans of toy figurines in arbitrary poses. We employ a novel part-based shape model to compute an initial registration to the scans. We then normalize their pose, learn a statistical shape model, and refine the registrations and the model together. In this way, we accurately align animal scans from different quadruped families with very different shapes and poses. With the registration to a common template we learn a shape space representing animals including lions, cats, dogs, horses, cows and hippos. Animal shapes can be sampled from the model, posed, animated, and fit to data. We demonstrate generalization by fitting it to images of real animals including species not seen in training.

pdf video Project Page [BibTex]

Zuffi, S., Kanazawa, A., Jacobs, D., Black, M. J. 3D Menagerie: Modeling the 3D Shape and Pose of Animals In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, pages: 5524-5532, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

pdf video Project Page [BibTex]

Thumb xl pyramid
Optical Flow Estimation using a Spatial Pyramid Network

Ranjan, A., Black, M.

In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

Abstract
We learn to compute optical flow by combining a classical spatial-pyramid formulation with deep learning. This estimates large motions in a coarse-to-fine approach by warping one image of a pair at each pyramid level by the current flow estimate and computing an update to the flow. Instead of the standard minimization of an objective function at each pyramid level, we train one deep network per level to compute the flow update. Unlike the recent FlowNet approach, the networks do not need to deal with large motions; these are dealt with by the pyramid. This has several advantages. First, our Spatial Pyramid Network (SPyNet) is much simpler and 96% smaller than FlowNet in terms of model parameters. This makes it more efficient and appropriate for embedded applications. Second, since the flow at each pyramid level is small (< 1 pixel), a convolutional approach applied to pairs of warped images is appropriate. Third, unlike FlowNet, the learned convolution filters appear similar to classical spatio-temporal filters, giving insight into the method and how to improve it. Our results are more accurate than FlowNet on most standard benchmarks, suggesting a new direction of combining classical flow methods with deep learning.

pdf SupMat project/code [BibTex]

Ranjan, A., Black, M. Optical Flow Estimation using a Spatial Pyramid Network In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

pdf SupMat project/code [BibTex]

Thumb xl imgidx 00197
Multiple People Tracking by Lifted Multicut and Person Re-identification

Tang, S., Andriluka, M., Andres, B., Schiele, B.

In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 3701-3710, IEEE Computer Society, Washington, DC, USA, July 2017 (inproceedings)

DOI Project Page [BibTex]

Tang, S., Andriluka, M., Andres, B., Schiele, B. Multiple People Tracking by Lifted Multicut and Person Re-identification In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 3701-3710, IEEE Computer Society, Washington, DC, USA, July 2017 (inproceedings)

DOI Project Page [BibTex]

Thumb xl vpn teaser
Video Propagation Networks

Jampani, V., Gadde, R., Gehler, P. V.

In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

pdf supplementary arXiv project page code Project Page [BibTex]

Jampani, V., Gadde, R., Gehler, P. V. Video Propagation Networks In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

pdf supplementary arXiv project page code Project Page [BibTex]

Thumb xl anja
Generating Descriptions with Grounded and Co-Referenced People

Rohrbach, A., Rohrbach, M., Tang, S., Oh, S. J., Schiele, B.

In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 4196-4206, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

PDF DOI Project Page [BibTex]

Rohrbach, A., Rohrbach, M., Tang, S., Oh, S. J., Schiele, B. Generating Descriptions with Grounded and Co-Referenced People In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 4196-4206, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

PDF DOI Project Page [BibTex]

Thumb xl cvpr2017 landpsace
Semantic Multi-view Stereo: Jointly Estimating Objects and Voxels

Ulusoy, A. O., Black, M. J., Geiger, A.

In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

Abstract
Dense 3D reconstruction from RGB images is a highly ill-posed problem due to occlusions, textureless or reflective surfaces, as well as other challenges. We propose object-level shape priors to address these ambiguities. Towards this goal, we formulate a probabilistic model that integrates multi-view image evidence with 3D shape information from multiple objects. Inference in this model yields a dense 3D reconstruction of the scene as well as the existence and precise 3D pose of the objects in it. Our approach is able to recover fine details not captured in the input shapes while defaulting to the input models in occluded regions where image evidence is weak. Due to its probabilistic nature, the approach is able to cope with the approximate geometry of the 3D models as well as input shapes that are not present in the scene. We evaluate the approach quantitatively on several challenging indoor and outdoor datasets.

YouTube pdf suppmat Project Page [BibTex]

Ulusoy, A. O., Black, M. J., Geiger, A. Semantic Multi-view Stereo: Jointly Estimating Objects and Voxels In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

YouTube pdf suppmat Project Page [BibTex]

Thumb xl judith
Deep representation learning for human motion prediction and classification

Bütepage, J., Black, M., Kragic, D., Kjellström, H.

In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

Abstract
Generative models of 3D human motion are often restricted to a small number of activities and can therefore not generalize well to novel movements or applications. In this work we propose a deep learning framework for human motion capture data that learns a generic representation from a large corpus of motion capture data and generalizes well to new, unseen, motions. Using an encoding-decoding network that learns to predict future 3D poses from the most recent past, we extract a feature representation of human motion. Most work on deep learning for sequence prediction focuses on video and speech. Since skeletal data has a different structure, we present and evaluate different network architectures that make different assumptions about time dependencies and limb correlations. To quantify the learned features, we use the output of different layers for action classification and visualize the receptive fields of the network units. Our method outperforms the recent state of the art in skeletal motion prediction even though these use action specific training data. Our results show that deep feedforward networks, trained from a generic mocap database, can successfully be used for feature extraction from human motion data and that this representation can be used as a foundation for classification and prediction.

arXiv Project Page [BibTex]

Bütepage, J., Black, M., Kragic, D., Kjellström, H. Deep representation learning for human motion prediction and classification In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

arXiv Project Page [BibTex]

Thumb xl teasercrop
Unite the People: Closing the Loop Between 3D and 2D Human Representations

Lassner, C., Romero, J., Kiefel, M., Bogo, F., Black, M. J., Gehler, P. V.

In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

Abstract
3D models provide a common ground for different representations of human bodies. In turn, robust 2D estimation has proven to be a powerful tool to obtain 3D fits “in-the-wild”. However, depending on the level of detail, it can be hard to impossible to acquire labeled data for training 2D estimators on large scale. We propose a hybrid approach to this problem: with an extended version of the recently introduced SMPLify method, we obtain high quality 3D body model fits for multiple human pose datasets. Human annotators solely sort good and bad fits. This procedure leads to an initial dataset, UP-3D, with rich annotations. With a comprehensive set of experiments, we show how this data can be used to train discriminative models that produce results with an unprecedented level of detail: our models predict 31 segments and 91 landmark locations on the body. Using the 91 landmark pose estimator, we present state-of-the art results for 3D human pose and shape estimation using an order of magnitude less training data and without assumptions about gender or pose in the fitting procedure. We show that UP-3D can be enhanced with these improved fits to grow in quantity and quality, which makes the system deployable on large scale. The data, code and models are available for research purposes.

arXiv project/code/data Project Page [BibTex]

Lassner, C., Romero, J., Kiefel, M., Bogo, F., Black, M. J., Gehler, P. V. Unite the People: Closing the Loop Between 3D and 2D Human Representations In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, July 2017 (inproceedings)

arXiv project/code/data Project Page [BibTex]

Thumb xl muvs
Towards Accurate Marker-less Human Shape and Pose Estimation over Time

Huang, Y., Bogo, F., Lassner, C., Kanazawa, A., Gehler, P. V., Romero, J., Akhter, I., Black, M. J.

In International Conference on 3D Vision (3DV), pages: 421-430, 2017 (inproceedings)

Abstract
Existing markerless motion capture methods often assume known backgrounds, static cameras, and sequence specific motion priors, limiting their application scenarios. Here we present a fully automatic method that, given multiview videos, estimates 3D human pose and body shape. We take the recently proposed SMPLify method [12] as the base method and extend it in several ways. First we fit a 3D human body model to 2D features detected in multi-view images. Second, we use a CNN method to segment the person in each image and fit the 3D body model to the contours, further improving accuracy. Third we utilize a generic and robust DCT temporal prior to handle the left and right side swapping issue sometimes introduced by the 2D pose estimator. Validation on standard benchmarks shows our results are comparable to the state of the art and also provide a realistic 3D shape avatar. We also demonstrate accurate results on HumanEva and on challenging monocular sequences of dancing from YouTube.

Code pdf DOI Project Page [BibTex]

2016

Thumb xl smplify
Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image

Bogo, F., Kanazawa, A., Lassner, C., Gehler, P., Romero, J., Black, M. J.

In Computer Vision – ECCV 2016, pages: 561-578, Lecture Notes in Computer Science, Springer International Publishing, October 2016 (inproceedings)

Abstract
We describe the first method to automatically estimate the 3D pose of the human body as well as its 3D shape from a single unconstrained image. We estimate a full 3D mesh and show that 2D joints alone carry a surprising amount of information about body shape. The problem is challenging because of the complexity of the human body, articulation, occlusion, clothing, lighting, and the inherent ambiguity in inferring 3D from 2D. To solve this, we fi rst use a recently published CNN-based method, DeepCut, to predict (bottom-up) the 2D body joint locations. We then fit (top-down) a recently published statistical body shape model, called SMPL, to the 2D joints. We do so by minimizing an objective function that penalizes the error between the projected 3D model joints and detected 2D joints. Because SMPL captures correlations in human shape across the population, we are able to robustly fi t it to very little data. We further leverage the 3D model to prevent solutions that cause interpenetration. We evaluate our method, SMPLify, on the Leeds Sports, HumanEva, and Human3.6M datasets, showing superior pose accuracy with respect to the state of the art.

pdf Video Sup Mat video Code Project Project Page [BibTex]

2016

Bogo, F., Kanazawa, A., Lassner, C., Gehler, P., Romero, J., Black, M. J. Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image In Computer Vision – ECCV 2016, pages: 561-578, Lecture Notes in Computer Science, Springer International Publishing, October 2016 (inproceedings)

pdf Video Sup Mat video Code Project Project Page [BibTex]

Thumb xl gadde
Superpixel Convolutional Networks using Bilateral Inceptions

Gadde, R., Jampani, V., Kiefel, M., Kappler, D., Gehler, P.

In European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science, Springer, October 2016 (inproceedings)

Abstract
In this paper we propose a CNN architecture for semantic image segmentation. We introduce a new “bilateral inception” module that can be inserted in existing CNN architectures and performs bilateral filtering, at multiple feature-scales, between superpixels in an image. The feature spaces for bilateral filtering and other parameters of the module are learned end-to-end using standard backpropagation techniques. The bilateral inception module addresses two issues that arise with general CNN segmentation architectures. First, this module propagates information between (super) pixels while respecting image edges, thus using the structured information of the problem for improved results. Second, the layer recovers a full resolution segmentation result from the lower resolution solution of a CNN. In the experiments, we modify several existing CNN architectures by inserting our inception modules between the last CNN (1 × 1 convolution) layers. Empirical results on three different datasets show reliable improvements not only in comparison to the baseline networks, but also in comparison to several dense-pixel prediction techniques such as CRFs, while being competitive in time.

pdf supplementary poster Project Page Project Page [BibTex]

Gadde, R., Jampani, V., Kiefel, M., Kappler, D., Gehler, P. Superpixel Convolutional Networks using Bilateral Inceptions In European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science, Springer, October 2016 (inproceedings)

pdf supplementary poster Project Page Project Page [BibTex]

Thumb xl thumb
Barrista - Caffe Well-Served

Lassner, C., Kappler, D., Kiefel, M., Gehler, P.

In ACM Multimedia Open Source Software Competition, October 2016 (inproceedings)

Abstract
The caffe framework is one of the leading deep learning toolboxes in the machine learning and computer vision community. While it offers efficiency and configurability, it falls short of a full interface to Python. With increasingly involved procedures for training deep networks and reaching depths of hundreds of layers, creating configuration files and keeping them consistent becomes an error prone process. We introduce the barrista framework, offering full, pythonic control over caffe. It separates responsibilities and offers code to solve frequently occurring tasks for pre-processing, training and model inspection. It is compatible to all caffe versions since mid 2015 and can import and export .prototxt files. Examples are included, e.g., a deep residual network implemented in only 172 lines (for arbitrary depths), comparing to 2320 lines in the official implementation for the equivalent model.

pdf link (url) DOI Project Page [BibTex]

Lassner, C., Kappler, D., Kiefel, M., Gehler, P. Barrista - Caffe Well-Served In ACM Multimedia Open Source Software Competition, October 2016 (inproceedings)

pdf link (url) DOI Project Page [BibTex]

Thumb xl cover
Dynamic baseline stereo vision-based cooperative target tracking

Ahmad, A., Ruff, E., Bülthoff, H.

19th International Conference on Information Fusion, pages: 1728-1734, July 2016 (conference)

Abstract
In this article we present a new method for multi-robot cooperative target tracking based on dynamic baseline stereo vision. The core novelty of our approach includes a computationally light-weight scheme to compute the 3D stereo measurements that exactly satisfy the epipolar constraints and a covariance intersection (CI)-based method to fuse the 3D measurements obtained by each individual robot. Using CI we are able to systematically integrate the robot localization uncertainties as well as the uncertainties in the measurements generated by the monocular camera images from each individual robot into the resulting stereo measurements. Through an extensive set of simulation and real robot results we show the robustness and accuracy of our approach with respect to ground truth. The source code related to this article is publicly accessible on our website and the datasets are available on request.

DOI [BibTex]

Ahmad, A., Ruff, E., Bülthoff, H. Dynamic baseline stereo vision-based cooperative target tracking 19th International Conference on Information Fusion, pages: 1728-1734, July 2016 (conference)

DOI [BibTex]

Thumb xl teaser
DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation

Pishchulin, L., Insafutdinov, E., Tang, S., Andres, B., Andriluka, M., Gehler, P., Schiele, B.

In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 4929-4937, IEEE, June 2016 (inproceedings)

Abstract
This paper considers the task of articulated human pose estimation of multiple people in real-world images. We propose an approach that jointly solves the tasks of detection and pose estimation: it infers the number of persons in a scene, identifies occluded body parts, and disambiguates body parts between people in close proximity of each other. This joint formulation is in contrast to previous strategies, that address the problem by first detecting people and subsequently estimating their body pose. We propose a partitioning and labeling formulation of a set of body-part hypotheses generated with CNN-based part detectors. Our formulation, an instance of an integer linear program, implicitly performs non-maximum suppression on the set of part candidates and groups them to form configurations of body parts respecting geometric and appearance constraints. Experiments on four different datasets demonstrate state-of-the-art results for both single person and multi person pose estimation.

code pdf supplementary DOI Project Page [BibTex]

Pishchulin, L., Insafutdinov, E., Tang, S., Andres, B., Andriluka, M., Gehler, P., Schiele, B. DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 4929-4937, IEEE, June 2016 (inproceedings)

code pdf supplementary DOI Project Page [BibTex]

Thumb xl tsaiteaser
Video segmentation via object flow

Tsai, Y., Yang, M., Black, M. J.

In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2016 (inproceedings)

Abstract
Video object segmentation is challenging due to fast moving objects, deforming shapes, and cluttered backgrounds. Optical flow can be used to propagate an object segmentation over time but, unfortunately, flow is often inaccurate, particularly around object boundaries. Such boundaries are precisely where we want our segmentation to be accurate. To obtain accurate segmentation across time, we propose an efficient algorithm that considers video segmentation and optical flow estimation simultaneously. For video segmentation, we formulate a principled, multiscale, spatio-temporal objective function that uses optical flow to propagate information between frames. For optical flow estimation, particularly at object boundaries, we compute the flow independently in the segmented regions and recompose the results. We call the process object flow and demonstrate the effectiveness of jointly optimizing optical flow and video segmentation using an iterative scheme. Experiments on the SegTrack v2 and Youtube-Objects datasets show that the proposed algorithm performs favorably against the other state-of-the-art methods.

pdf [BibTex]

Tsai, Y., Yang, M., Black, M. J. Video segmentation via object flow In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2016 (inproceedings)

pdf [BibTex]

Thumb xl capital
Patches, Planes and Probabilities: A Non-local Prior for Volumetric 3D Reconstruction

Ulusoy, A. O., Black, M. J., Geiger, A.

In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2016 (inproceedings)

Abstract
In this paper, we propose a non-local structured prior for volumetric multi-view 3D reconstruction. Towards this goal, we present a novel Markov random field model based on ray potentials in which assumptions about large 3D surface patches such as planarity or Manhattan world constraints can be efficiently encoded as probabilistic priors. We further derive an inference algorithm that reasons jointly about voxels, pixels and image segments, and estimates marginal distributions of appearance, occupancy, depth, normals and planarity. Key to tractable inference is a novel hybrid representation that spans both voxel and pixel space and that integrates non-local information from 2D image segmentations in a principled way. We compare our non-local prior to commonly employed local smoothness assumptions and a variety of state-of-the-art volumetric reconstruction baselines on challenging outdoor scenes with textureless and reflective surfaces. Our experiments indicate that regularizing over larger distances has the potential to resolve ambiguities where local regularizers fail.

YouTube pdf poster suppmat Project Page [BibTex]