Header logo is ps


2017


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]

2017

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]

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]

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]

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]

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]

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]

arXiv project/code/data Project Page [BibTex]


Thumb xl dapepatent
System and method for simulating realistic clothing

Black, M. J., Guan, P.

June 2017, U.S.~Patent 9,679,409 B2 (misc)

Abstract
Systems, methods, and computer-readable storage media for simulating realistic clothing. The system generates a clothing deformation model for a clothing type, wherein the clothing deformation model factors a change of clothing shape due to rigid limb rotation, pose-independent body shape, and pose-dependent deformations. Next, the system generates a custom-shaped garment for a given body by mapping, via the clothing deformation model, body shape parameters to clothing shape parameters. The system then automatically dresses the given body with the custom- shaped garment.

Google Patents pdf [BibTex]


Thumb xl image  1
Human Shape Estimation using Statistical Body Models

Loper, M. M.

University of Tübingen, May 2017 (thesis)

Abstract
Human body estimation methods transform real-world observations into predictions about human body state. These estimation methods benefit a variety of health, entertainment, clothing, and ergonomics applications. State may include pose, overall body shape, and appearance. Body state estimation is underconstrained by observations; ambiguity presents itself both in the form of missing data within observations, and also in the form of unknown correspondences between observations. We address this challenge with the use of a statistical body model: a data-driven virtual human. This helps resolve ambiguity in two ways. First, it fills in missing data, meaning that incomplete observations still result in complete shape estimates. Second, the model provides a statistically-motivated penalty for unlikely states, which enables more plausible body shape estimates. Body state inference requires more than a body model; we therefore build obser- vation models whose output is compared with real observations. In this thesis, body state is estimated from three types of observations: 3D motion capture markers, depth and color images, and high-resolution 3D scans. In each case, a forward process is proposed which simulates observations. By comparing observations to the results of the forward process, state can be adjusted to minimize the difference between simulated and observed data. We use gradient-based methods because they are critical to the precise estimation of state with a large number of parameters. The contributions of this work include three parts. First, we propose a method for the estimation of body shape, nonrigid deformation, and pose from 3D markers. Second, we present a concise approach to differentiating through the rendering process, with application to body shape estimation. And finally, we present a statistical body model trained from human body scans, with state-of-the-art fidelity, good runtime performance, and compatibility with existing animation packages.

Official Version [BibTex]


Thumb xl early stopping teaser
Early Stopping Without a Validation Set

Mahsereci, M., Balles, L., Lassner, C., Hennig, P.

arXiv preprint arXiv:1703.09580, 2017 (article)

Abstract
Early stopping is a widely used technique to prevent poor generalization performance when training an over-expressive model by means of gradient-based optimization. To find a good point to halt the optimizer, a common practice is to split the dataset into a training and a smaller validation set to obtain an ongoing estimate of the generalization performance. In this paper we propose a novel early stopping criterion which is based on fast-to-compute, local statistics of the computed gradients and entirely removes the need for a held-out validation set. Our experiments show that this is a viable approach in the setting of least-squares and logistic regression as well as neural networks.

link (url) Project Page Project Page [BibTex]


Thumb xl appealingavatars
Appealing Avatars from 3D Body Scans: Perceptual Effects of Stylization

Fleming, R., Mohler, B. J., Romero, J., Black, M. J., Breidt, M.

In Computer Vision, Imaging and Computer Graphics Theory and Applications: 11th International Joint Conference, VISIGRAPP 2016, Rome, Italy, February 27 – 29, 2016, Revised Selected Papers, pages: 175-196, Springer International Publishing, 2017 (inbook)

Abstract
Using styles derived from existing popular character designs, we present a novel automatic stylization technique for body shape and colour information based on a statistical 3D model of human bodies. We investigate whether such stylized body shapes result in increased perceived appeal with two different experiments: One focuses on body shape alone, the other investigates the additional role of surface colour and lighting. Our results consistently show that the most appealing avatar is a partially stylized one. Importantly, avatars with high stylization or no stylization at all were rated to have the least appeal. The inclusion of colour information and improvements to render quality had no significant effect on the overall perceived appeal of the avatars, and we observe that the body shape primarily drives the change in appeal ratings. For body scans with colour information, we found that a partially stylized avatar was perceived as most appealing.

publisher site pdf DOI [BibTex]

publisher site pdf DOI [BibTex]


Thumb xl gcpr2017 nugget
Learning to Filter Object Detections

Prokudin, S., Kappler, D., Nowozin, S., Gehler, P.

In Pattern Recognition: 39th German Conference, GCPR 2017, Basel, Switzerland, September 12–15, 2017, Proceedings, pages: 52-62, Springer International Publishing, Cham, 2017 (inbook)

Abstract
Most object detection systems consist of three stages. First, a set of individual hypotheses for object locations is generated using a proposal generating algorithm. Second, a classifier scores every generated hypothesis independently to obtain a multi-class prediction. Finally, all scored hypotheses are filtered via a non-differentiable and decoupled non-maximum suppression (NMS) post-processing step. In this paper, we propose a filtering network (FNet), a method which replaces NMS with a differentiable neural network that allows joint reasoning and re-scoring of the generated set of hypotheses per image. This formulation enables end-to-end training of the full object detection pipeline. First, we demonstrate that FNet, a feed-forward network architecture, is able to mimic NMS decisions, despite the sequential nature of NMS. We further analyze NMS failures and propose a loss formulation that is better aligned with the mean average precision (mAP) evaluation metric. We evaluate FNet on several standard detection datasets. Results surpass standard NMS on highly occluded settings of a synthetic overlapping MNIST dataset and show competitive behavior on PascalVOC2007 and KITTI detection benchmarks.

Paper link (url) DOI Project Page [BibTex]

Paper link (url) DOI Project Page [BibTex]


Thumb xl web image
Data-Driven Physics for Human Soft Tissue Animation

Kim, M., Pons-Moll, G., Pujades, S., Bang, S., Kim, J., Black, M. J., Lee, S.

ACM Transactions on Graphics, (Proc. SIGGRAPH), 36(4):54:1-54:12, 2017 (article)

Abstract
Data driven models of human poses and soft-tissue deformations can produce very realistic results, but they only model the visible surface of the human body and cannot create skin deformation due to interactions with the environment. Physical simulations can generalize to external forces, but their parameters are difficult to control. In this paper, we present a layered volumetric human body model learned from data. Our model is composed of a data-driven inner layer and a physics-based external layer. The inner layer is driven with a volumetric statistical body model (VSMPL). The soft tissue layer consists of a tetrahedral mesh that is driven using the finite element method (FEM). Model parameters, namely the segmentation of the body into layers and the soft tissue elasticity, are learned directly from 4D registrations of humans exhibiting soft tissue deformations. The learned two layer model is a realistic full-body avatar that generalizes to novel motions and external forces. Experiments show that the resulting avatars produce realistic results on held out sequences and react to external forces. Moreover, the model supports the retargeting of physical properties from one avatar when they share the same topology.

video paper link (url) Project Page [BibTex]

video paper link (url) Project Page [BibTex]


Thumb xl phd thesis teaser
Learning Inference Models for Computer Vision

Jampani, V.

MPI for Intelligent Systems and University of Tübingen, 2017 (phdthesis)

Abstract
Computer vision can be understood as the ability to perform 'inference' on image data. Breakthroughs in computer vision technology are often marked by advances in inference techniques, as even the model design is often dictated by the complexity of inference in them. This thesis proposes learning based inference schemes and demonstrates applications in computer vision. We propose techniques for inference in both generative and discriminative computer vision models. Despite their intuitive appeal, the use of generative models in vision is hampered by the difficulty of posterior inference, which is often too complex or too slow to be practical. We propose techniques for improving inference in two widely used techniques: Markov Chain Monte Carlo (MCMC) sampling and message-passing inference. Our inference strategy is to learn separate discriminative models that assist Bayesian inference in a generative model. Experiments on a range of generative vision models show that the proposed techniques accelerate the inference process and/or converge to better solutions. A main complication in the design of discriminative models is the inclusion of prior knowledge in a principled way. For better inference in discriminative models, we propose techniques that modify the original model itself, as inference is simple evaluation of the model. We concentrate on convolutional neural network (CNN) models and propose a generalization of standard spatial convolutions, which are the basic building blocks of CNN architectures, to bilateral convolutions. First, we generalize the existing use of bilateral filters and then propose new neural network architectures with learnable bilateral filters, which we call `Bilateral Neural Networks'. We show how the bilateral filtering modules can be used for modifying existing CNN architectures for better image segmentation and propose a neural network approach for temporal information propagation in videos. Experiments demonstrate the potential of the proposed bilateral networks on a wide range of vision tasks and datasets. In summary, we propose learning based techniques for better inference in several computer vision models ranging from inverse graphics to freely parameterized neural networks. In generative vision models, our inference techniques alleviate some of the crucial hurdles in Bayesian posterior inference, paving new ways for the use of model based machine learning in vision. In discriminative CNN models, the proposed filter generalizations aid in the design of new neural network architectures that can handle sparse high-dimensional data as well as provide a way for incorporating prior knowledge into CNNs.

pdf [BibTex]

pdf [BibTex]


Thumb xl web teaser eg
Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUs

(Best Paper, Eurographics 2017)

Marcard, T. V., Rosenhahn, B., Black, M., Pons-Moll, G.

Computer Graphics Forum 36(2), Proceedings of the 38th Annual Conference of the European Association for Computer Graphics (Eurographics), pages: 349-360 , 2017 (article)

Abstract
We address the problem of making human motion capture in the wild more practical by using a small set of inertial sensors attached to the body. Since the problem is heavily under-constrained, previous methods either use a large number of sensors, which is intrusive, or they require additional video input. We take a different approach and constrain the problem by: (i) making use of a realistic statistical body model that includes anthropometric constraints and (ii) using a joint optimization framework to fit the model to orientation and acceleration measurements over multiple frames. The resulting tracker Sparse Inertial Poser (SIP) enables motion capture using only 6 sensors (attached to the wrists, lower legs, back and head) and works for arbitrary human motions. Experiments on the recently released TNT15 dataset show that, using the same number of sensors, SIP achieves higher accuracy than the dataset baseline without using any video data. We further demonstrate the effectiveness of SIP on newly recorded challenging motions in outdoor scenarios such as climbing or jumping over a wall

video pdf Project Page [BibTex]

video pdf Project Page [BibTex]


Thumb xl pami 2017 teaser
Efficient 2D and 3D Facade Segmentation using Auto-Context

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

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017 (article)

Abstract
This paper introduces a fast and efficient segmentation technique for 2D images and 3D point clouds of building facades. Facades of buildings are highly structured and consequently most methods that have been proposed for this problem aim to make use of this strong prior information. Contrary to most prior work, we are describing a system that is almost domain independent and consists of standard segmentation methods. We train a sequence of boosted decision trees using auto-context features. This is learned using stacked generalization. We find that this technique performs better, or comparable with all previous published methods and present empirical results on all available 2D and 3D facade benchmark datasets. The proposed method is simple to implement, easy to extend, and very efficient at test-time inference.

arXiv Project Page [BibTex]

arXiv Project Page [BibTex]


Thumb xl web image
ClothCap: Seamless 4D Clothing Capture and Retargeting

Pons-Moll, G., Pujades, S., Hu, S., Black, M.

ACM Transactions on Graphics, (Proc. SIGGRAPH), 36(4):73:1-73:15, ACM, New York, NY, USA, 2017, Two first authors contributed equally (article)

Abstract
Designing and simulating realistic clothing is challenging and, while several methods have addressed the capture of clothing from 3D scans, previous methods have been limited to single garments and simple motions, lack detail, or require specialized texture patterns. Here we address the problem of capturing regular clothing on fully dressed people in motion. People typically wear multiple pieces of clothing at a time. To estimate the shape of such clothing, track it over time, and render it believably, each garment must be segmented from the others and the body. Our ClothCap approach uses a new multi-part 3D model of clothed bodies, automatically segments each piece of clothing, estimates the naked body shape and pose under the clothing, and tracks the 3D deformations of the clothing over time. We estimate the garments and their motion from 4D scans; that is, high-resolution 3D scans of the subject in motion at 60 fps. The model allows us to capture a clothed person in motion, extract their clothing, and retarget the clothing to new body shapes. ClothCap provides a step towards virtual try-on with a technology for capturing, modeling, and analyzing clothing in motion.

video project_page paper link (url) DOI Project Page Project Page [BibTex]

video project_page paper link (url) DOI Project Page 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]


Thumb xl auroteaser
Decentralized Simultaneous Multi-target Exploration using a Connected Network of Multiple Robots

Nestmeyer, T., Robuffo Giordano, P., Bülthoff, H. H., Franchi, A.

In pages: 989-1011, Autonomous Robots, 2017 (incollection)

[BibTex]

[BibTex]


Thumb xl coverhand wilson
Capturing Hand-Object Interaction and Reconstruction of Manipulated Objects

Tzionas, D.

University of Bonn, 2017 (phdthesis)

Abstract
Hand motion capture with an RGB-D sensor gained recently a lot of research attention, however, even most recent approaches focus on the case of a single isolated hand. We focus instead on hands that interact with other hands or with a rigid or articulated object. Our framework successfully captures motion in such scenarios by combining a generative model with discriminatively trained salient points, collision detection and physics simulation to achieve a low tracking error with physically plausible poses. All components are unified in a single objective function that can be optimized with standard optimization techniques. We initially assume a-priori knowledge of the object's shape and skeleton. In case of unknown object shape there are existing 3d reconstruction methods that capitalize on distinctive geometric or texture features. These methods though fail for textureless and highly symmetric objects like household articles, mechanical parts or toys. We show that extracting 3d hand motion for in-hand scanning effectively facilitates the reconstruction of such objects and we fuse the rich additional information of hands into a 3d reconstruction pipeline. Finally, although shape reconstruction is enough for rigid objects, there is a lack of tools that build rigged models of articulated objects that deform realistically using RGB-D data. We propose a method that creates a fully rigged model consisting of a watertight mesh, embedded skeleton and skinning weights by employing a combination of deformable mesh tracking, motion segmentation based on spectral clustering and skeletonization based on mean curvature flow.

Thesis link (url) Project Page [BibTex]

2016


Thumb xl smpl
Skinned multi-person linear model

Black, M.J., Loper, M., Mahmood, N., Pons-Moll, G., Romero, J.

December 2016, Application PCT/EP2016/064610 (misc)

Abstract
The invention comprises a learned model of human body shape and pose dependent shape variation that is more accurate than previous models and is compatible with existing graphics pipelines. Our Skinned Multi-Person Linear model (SMPL) is a skinned vertex based model that accurately represents a wide variety of body shapes in natural human poses. The parameters of the model are learned from data including the rest pose template, blend weights, pose-dependent blend shapes, identity- dependent blend shapes, and a regressor from vertices to joint locations. Unlike previous models, the pose-dependent blend shapes are a linear function of the elements of the pose rotation matrices. This simple formulation enables training the entire model from a relatively large number of aligned 3D meshes of different people in different poses. The invention quantitatively evaluates variants of SMPL using linear or dual- quaternion blend skinning and show that both are more accurate than a Blend SCAPE model trained on the same data. In a further embodiment, the invention realistically models dynamic soft-tissue deformations. Because it is based on blend skinning, SMPL is compatible with existing rendering engines and we make it available for research purposes.

Google Patents [BibTex]

2016

Google Patents [BibTex]


Thumb xl psychscience
Creating body shapes from verbal descriptions by linking similarity spaces

Hill, M. Q., Streuber, S., Hahn, C. A., Black, M. J., O’Toole, A. J.

Psychological Science, 27(11):1486-1497, November 2016, (article)

Abstract
Brief verbal descriptions of bodies (e.g. curvy, long-legged) can elicit vivid mental images. The ease with which we create these mental images belies the complexity of three-dimensional body shapes. We explored the relationship between body shapes and body descriptions and show that a small number of words can be used to generate categorically accurate representations of three-dimensional bodies. The dimensions of body shape variation that emerged in a language-based similarity space were related to major dimensions of variation computed directly from three-dimensional laser scans of 2094 bodies. This allowed us to generate three-dimensional models of people in the shape space using only their coordinates on analogous dimensions in the language-based description space. Human descriptions of photographed bodies and their corresponding models matched closely. The natural mapping between the spaces illustrates the role of language as a concise code for body shape, capturing perceptually salient global and local body features.

pdf [BibTex]

pdf [BibTex]


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]

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]

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]

pdf link (url) DOI Project Page [BibTex]


Thumb xl screen shot 2016 07 25 at 13.52.05
Non-parametric Models for Structured Data and Applications to Human Bodies and Natural Scenes

Lehrmann, A.

ETH Zurich, July 2016 (phdthesis)

Abstract
The purpose of this thesis is the study of non-parametric models for structured data and their fields of application in computer vision. We aim at the development of context-sensitive architectures which are both expressive and efficient. Our focus is on directed graphical models, in particular Bayesian networks, where we combine the flexibility of non-parametric local distributions with the efficiency of a global topology with bounded treewidth. A bound on the treewidth is obtained by either constraining the maximum indegree of the underlying graph structure or by introducing determinism. The non-parametric distributions in the nodes of the graph are given by decision trees or kernel density estimators. The information flow implied by specific network topologies, especially the resultant (conditional) independencies, allows for a natural integration and control of contextual information. We distinguish between three different types of context: static, dynamic, and semantic. In four different approaches we propose models which exhibit varying combinations of these contextual properties and allow modeling of structured data in space, time, and hierarchies derived thereof. The generative character of the presented models enables a direct synthesis of plausible hypotheses. Extensive experiments validate the developed models in two application scenarios which are of particular interest in computer vision: human bodies and natural scenes. In the practical sections of this work we discuss both areas from different angles and show applications of our models to human pose, motion, and segmentation as well as object categorization and localization. Here, we benefit from the availability of modern datasets of unprecedented size and diversity. Comparisons to traditional approaches and state-of-the-art research on the basis of well-established evaluation criteria allows the objective assessment of our contributions.

pdf [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]

DOI [BibTex]


Thumb xl webteaser
Body Talk: Crowdshaping Realistic 3D Avatars with Words

Streuber, S., Quiros-Ramirez, M. A., Hill, M. Q., Hahn, C. A., Zuffi, S., O’Toole, A., Black, M. J.

ACM Trans. Graph. (Proc. SIGGRAPH), 35(4):54:1-54:14, July 2016 (article)

Abstract
Realistic, metrically accurate, 3D human avatars are useful for games, shopping, virtual reality, and health applications. Such avatars are not in wide use because solutions for creating them from high-end scanners, low-cost range cameras, and tailoring measurements all have limitations. Here we propose a simple solution and show that it is surprisingly accurate. We use crowdsourcing to generate attribute ratings of 3D body shapes corresponding to standard linguistic descriptions of 3D shape. We then learn a linear function relating these ratings to 3D human shape parameters. Given an image of a new body, we again turn to the crowd for ratings of the body shape. The collection of linguistic ratings of a photograph provides remarkably strong constraints on the metric 3D shape. We call the process crowdshaping and show that our Body Talk system produces shapes that are perceptually indistinguishable from bodies created from high-resolution scans and that the metric accuracy is sufficient for many tasks. This makes body “scanning” practical without a scanner, opening up new applications including database search, visualization, and extracting avatars from books.

pdf web tool video talk (ppt) [BibTex]

pdf web tool video talk (ppt) [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]

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]

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]


Thumb xl ijcv tumb
Capturing Hands in Action using Discriminative Salient Points and Physics Simulation

Tzionas, D., Ballan, L., Srikantha, A., Aponte, P., Pollefeys, M., Gall, J.

International Journal of Computer Vision (IJCV), 118(2):172-193, June 2016 (article)

Abstract
Hand motion capture is a popular research field, recently gaining more attention due to the ubiquity of RGB-D sensors. However, even most recent approaches focus on the case of a single isolated hand. In this work, we focus on hands that interact with other hands or objects and present a framework that successfully captures motion in such interaction scenarios for both rigid and articulated objects. Our framework combines a generative model with discriminatively trained salient points to achieve a low tracking error and with collision detection and physics simulation to achieve physically plausible estimates even in case of occlusions and missing visual data. Since all components are unified in a single objective function which is almost everywhere differentiable, it can be optimized with standard optimization techniques. Our approach works for monocular RGB-D sequences as well as setups with multiple synchronized RGB cameras. For a qualitative and quantitative evaluation, we captured 29 sequences with a large variety of interactions and up to 150 degrees of freedom.

Website pdf link (url) DOI Project Page [BibTex]

Website pdf link (url) DOI Project Page [BibTex]


Thumb xl header
Optical Flow with Semantic Segmentation and Localized Layers

Sevilla-Lara, L., Sun, D., Jampani, V., Black, M. J.

In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pages: 3889-3898, June 2016 (inproceedings)

Abstract
Existing optical flow methods make generic, spatially homogeneous, assumptions about the spatial structure of the flow. In reality, optical flow varies across an image depending on object class. Simply put, different objects move differently. Here we exploit recent advances in static semantic scene segmentation to segment the image into objects of different types. We define different models of image motion in these regions depending on the type of object. For example, we model the motion on roads with homographies, vegetation with spatially smooth flow, and independently moving objects like cars and planes with affine motion plus deviations. We then pose the flow estimation problem using a novel formulation of localized layers, which addresses limitations of traditional layered models for dealing with complex scene motion. Our semantic flow method achieves the lowest error of any published monocular method in the KITTI-2015 flow benchmark and produces qualitatively better flow and segmentation than recent top methods on a wide range of natural videos.

video Kitti Precomputed Data (1.6GB) pdf YouTube Sequences Code Project Page Project Page [BibTex]


Thumb xl tes cvpr16 bilateral
Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks

Jampani, V., Kiefel, M., Gehler, P. V.

In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pages: 4452-4461, June 2016 (inproceedings)

Abstract
Bilateral filters have wide spread use due to their edge-preserving properties. The common use case is to manually choose a parametric filter type, usually a Gaussian filter. In this paper, we will generalize the parametrization and in particular derive a gradient descent algorithm so the filter parameters can be learned from data. This derivation allows to learn high dimensional linear filters that operate in sparsely populated feature spaces. We build on the permutohedral lattice construction for efficient filtering. The ability to learn more general forms of high-dimensional filters can be used in several diverse applications. First, we demonstrate the use in applications where single filter applications are desired for runtime reasons. Further, we show how this algorithm can be used to learn the pairwise potentials in densely connected conditional random fields and apply these to different image segmentation tasks. Finally, we introduce layers of bilateral filters in CNNs and propose bilateral neural networks for the use of high-dimensional sparse data. This view provides new ways to encode model structure into network architectures. A diverse set of experiments empirically validates the usage of general forms of filters.

project page code CVF open-access pdf supplementary poster Project Page Project Page [BibTex]


Thumb xl futeaser
Occlusion boundary detection via deep exploration of context

Fu, H., Wang, C., Tao, D., Black, M. J.

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

Abstract
Occlusion boundaries contain rich perceptual information about the underlying scene structure. They also provide important cues in many visual perception tasks such as scene understanding, object recognition, and segmentation. In this paper, we improve occlusion boundary detection via enhanced exploration of contextual information (e.g., local structural boundary patterns, observations from surrounding regions, and temporal context), and in doing so develop a novel approach based on convolutional neural networks (CNNs) and conditional random fields (CRFs). Experimental results demonstrate that our detector significantly outperforms the state-of-the-art (e.g., improving the F-measure from 0.62 to 0.71 on the commonly used CMU benchmark). Last but not least, we empirically assess the roles of several important components of the proposed detector, so as to validate the rationale behind this approach.

pdf [BibTex]

pdf [BibTex]


Thumb xl jun teaser
Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer

Xie, J., Kiefel, M., Sun, M., Geiger, A.

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

Abstract
Semantic annotations are vital for training models for object recognition, semantic segmentation or scene understanding. Unfortunately, pixelwise annotation of images at very large scale is labor-intensive and only little labeled data is available, particularly at instance level and for street scenes. In this paper, we propose to tackle this problem by lifting the semantic instance labeling task from 2D into 3D. Given reconstructions from stereo or laser data, we annotate static 3D scene elements with rough bounding primitives and develop a probabilistic model which transfers this information into the image domain. We leverage our method to obtain 2D labels for a novel suburban video dataset which we have collected, resulting in 400k semantic and instance image annotations. A comparison of our method to state-of-the-art label transfer baselines reveals that 3D information enables more efficient annotation while at the same time resulting in improved accuracy and time-coherent labels.

pdf suppmat Project Page Project Page [BibTex]

pdf suppmat Project Page Project Page [BibTex]


Thumb xl appealingavatarsbig
Appealing female avatars from 3D body scans: Perceptual effects of stylization

Fleming, R., Mohler, B., Romero, J., Black, M. J., Breidt, M.

In 11th Int. Conf. on Computer Graphics Theory and Applications (GRAPP), Febuary 2016 (inproceedings)

Abstract
Advances in 3D scanning technology allow us to create realistic virtual avatars from full body 3D scan data. However, negative reactions to some realistic computer generated humans suggest that this approach might not always provide the most appealing results. Using styles derived from existing popular character designs, we present a novel automatic stylization technique for body shape and colour information based on a statistical 3D model of human bodies. We investigate whether such stylized body shapes result in increased perceived appeal with two different experiments: One focuses on body shape alone, the other investigates the additional role of surface colour and lighting. Our results consistently show that the most appealing avatar is a partially stylized one. Importantly, avatars with high stylization or no stylization at all were rated to have the least appeal. The inclusion of colour information and improvements to render quality had no significant effect on the overall perceived appeal of the avatars, and we observe that the body shape primarily drives the change in appeal ratings. For body scans with colour information, we found that a partially stylized avatar was most effective, increasing average appeal ratings by approximately 34%.

pdf Project Page [BibTex]

pdf Project Page [BibTex]


Thumb xl teaser web
Human Pose Estimation from Video and IMUs

Marcard, T. V., Pons-Moll, G., Rosenhahn, B.

Transactions on Pattern Analysis and Machine Intelligence PAMI, 38(8):1533-1547, January 2016 (article)

data pdf dataset_documentation [BibTex]

data pdf dataset_documentation [BibTex]


Thumb xl teaser
Deep Discrete Flow

Güney, F., Geiger, A.

Asian Conference on Computer Vision (ACCV), 2016 (conference) Accepted

pdf suppmat Project Page [BibTex]

pdf suppmat Project Page [BibTex]


Thumb xl both testbed cropped
Moving-horizon Nonlinear Least Squares-based Multirobot Cooperative Perception

Ahmad, A., Bülthoff, H.

Robotics and Autonomous Systems, 83, pages: 275-286, 2016 (article)

Abstract
In this article we present an online estimator for multirobot cooperative localization and target tracking based on nonlinear least squares minimization. Our method not only makes the rigorous optimization-based approach applicable online but also allows the estimator to be stable and convergent. We do so by employing a moving horizon technique to nonlinear least squares minimization and a novel design of the arrival cost function that ensures stability and convergence of the estimator. Through an extensive set of real robot experiments, we demonstrate the robustness of our method as well as the optimality of the arrival cost function. The experiments include comparisons of our method with i) an extended Kalman filter-based online-estimator and ii) an offline-estimator based on full-trajectory nonlinear least squares.

DOI Project Page [BibTex]

DOI Project Page [BibTex]


Thumb xl sabteaser
Perceiving Systems (2011-2015)
Scientific Advisory Board Report, 2016 (misc)

pdf [BibTex]

pdf [BibTex]


Thumb xl siyong
Shape estimation of subcutaneous adipose tissue using an articulated statistical shape model

Yeo, S. Y., Romero, J., Loper, M., Machann, J., Black, M.

Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 0(0):1-8, 2016 (article)

publisher website preprint pdf link (url) DOI Project Page [BibTex]

publisher website preprint pdf link (url) DOI Project Page [BibTex]


Thumb xl siyu eccvw
Multi-Person Tracking by Multicuts and Deep Matching

(Winner of the Multi-Object Tracking Challenge ECCV 2016)

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

ECCV Workshop on Benchmarking Mutliple Object Tracking, 2016 (conference)

PDF [BibTex]

PDF [BibTex]


Thumb xl website thumbnail
Reconstructing Articulated Rigged Models from RGB-D Videos

Tzionas, D., Gall, J.

In European Conference on Computer Vision Workshops 2016 (ECCVW’16) - Workshop on Recovering 6D Object Pose (R6D’16), pages: 620-633, Springer International Publishing, 2016 (inproceedings)

Abstract
Although commercial and open-source software exist to reconstruct a static object from a sequence recorded with an RGB-D sensor, there is a lack of tools that build rigged models of articulated objects that deform realistically and can be used for tracking or animation. In this work, we fill this gap and propose a method that creates a fully rigged model of an articulated object from depth data of a single sensor. To this end, we combine deformable mesh tracking, motion segmentation based on spectral clustering and skeletonization based on mean curvature flow. The fully rigged model then consists of a watertight mesh, embedded skeleton, and skinning weights.

pdf suppl Project's Website YouTube link (url) DOI [BibTex]

pdf suppl Project's Website YouTube link (url) DOI [BibTex]


Thumb xl jointmc
A Multi-cut Formulation for Joint Segmentation and Tracking of Multiple Objects

Keuper, M., Tang, S., Yu, Z., Andres, B., Brox, T., Schiele, B.

In arXiv:1607.06317, 2016 (inproceedings)

PDF [BibTex]

PDF [BibTex]


Thumb xl screen shot 2016 02 22 at 11.46.41
The GRASP Taxonomy of Human Grasp Types

Feix, T., Romero, J., Schmiedmayer, H., Dollar, A., Kragic, D.

Human-Machine Systems, IEEE Transactions on, 46(1):66-77, 2016 (article)

publisher website pdf DOI Project Page [BibTex]

publisher website pdf DOI Project Page [BibTex]


Thumb xl pami
Map-Based Probabilistic Visual Self-Localization

Brubaker, M. A., Geiger, A., Urtasun, R.

IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI), 2016 (article)

Abstract
Accurate and efficient self-localization is a critical problem for autonomous systems. This paper describes an affordable solution to vehicle self-localization which uses odometry computed from two video cameras and road maps as the sole inputs. The core of the method is a probabilistic model for which an efficient approximate inference algorithm is derived. The inference algorithm is able to utilize distributed computation in order to meet the real-time requirements of autonomous systems in some instances. Because of the probabilistic nature of the model the method is capable of coping with various sources of uncertainty including noise in the visual odometry and inherent ambiguities in the map (e.g., in a Manhattan world). By exploiting freely available, community developed maps and visual odometry measurements, the proposed method is able to localize a vehicle to 4m on average after 52 seconds of driving on maps which contain more than 2,150km of drivable roads.

pdf Project Page [BibTex]

pdf Project Page [BibTex]

2013


Thumb xl iccv2013 siyu
Learning People Detectors for Tracking in Crowded Scenes

Tang, S., Andriluka, M., Milan, A., Schindler, K., Roth, S., Schiele, B.

In 2013 IEEE International Conference on Computer Vision, pages: 1049-1056, IEEE, December 2013 (inproceedings)

PDF DOI [BibTex]

2013

PDF DOI [BibTex]


Thumb xl thumb
Branch&Rank for Efficient Object Detection

Lehmann, A., Gehler, P., VanGool, L.

International Journal of Computer Vision, Springer, December 2013 (article)

Abstract
Ranking hypothesis sets is a powerful concept for efficient object detection. In this work, we propose a branch&rank scheme that detects objects with often less than 100 ranking operations. This efficiency enables the use of strong and also costly classifiers like non-linear SVMs with RBF-TeX kernels. We thereby relieve an inherent limitation of branch&bound methods as bounds are often not tight enough to be effective in practice. Our approach features three key components: a ranking function that operates on sets of hypotheses and a grouping of these into different tasks. Detection efficiency results from adaptively sub-dividing the object search space into decreasingly smaller sets. This is inherited from branch&bound, while the ranking function supersedes a tight bound which is often unavailable (except for rather limited function classes). The grouping makes the system effective: it separates image classification from object recognition, yet combines them in a single formulation, phrased as a structured SVM problem. A novel aspect of branch&rank is that a better ranking function is expected to decrease the number of classifier calls during detection. We use the VOC’07 dataset to demonstrate the algorithmic properties of branch&rank.

pdf link (url) [BibTex]

pdf link (url) [BibTex]


Thumb xl thumb
Strong Appearance and Expressive Spatial Models for Human Pose Estimation

Pishchulin, L., Andriluka, M., Gehler, P., Schiele, B.

In International Conference on Computer Vision (ICCV), pages: 3487 - 3494 , IEEE, December 2013 (inproceedings)

Abstract
Typical approaches to articulated pose estimation combine spatial modelling of the human body with appearance modelling of body parts. This paper aims to push the state-of-the-art in articulated pose estimation in two ways. First we explore various types of appearance representations aiming to substantially improve the body part hypotheses. And second, we draw on and combine several recently proposed powerful ideas such as more flexible spatial models as well as image-conditioned spatial models. In a series of experiments we draw several important conclusions: (1) we show that the proposed appearance representations are complementary; (2) we demonstrate that even a basic tree-structure spatial human body model achieves state-of-the-art performance when augmented with the proper appearance representation; and (3) we show that the combination of the best performing appearance model with a flexible image-conditioned spatial model achieves the best result, significantly improving over the state of the art, on the "Leeds Sports Poses'' and "Parse'' benchmarks.

pdf DOI Project Page [BibTex]

pdf DOI Project Page [BibTex]