Deep learning has significantly advanced state-of-the-art for 3D hand pose estimation, of which accuracy can be improved with increased amounts of labelled data. However, acquiring 3D hand pose labels can be extremely difficult. In this talk, I will present our recent two works on leveraging self-supervised learning techniques for hand pose estimation from depth map. In both works, we incorporate differentiable renderer to the network and formulate training loss as model fitting error to update network parameters. In first part of the talk, I will present our earlier work which approximates hand surface with a set of spheres. We then model the pose prior as a variational lower bound with variational auto-encoder(VAE). In second part, I will present our latest work on regressing the vertex coordinates of a hand mesh model with 2D fully convolutional network(FCN) in a single forward pass. In the first stage, the network estimates a dense correspondence field for every pixel on the image grid to the mesh grid. In the second stage, we design a differentiable operator to map features learned from the previous stage and regress a 3D coordinate map on the mesh grid. Finally, we sample from the mesh grid to recover the mesh vertices, and fit it an articulated template mesh in closed form. Without any human annotation, both works can perform competitively with strongly supervised methods. The later work will also be later extended to be compatible with MANO model.
Organizers: Dimitrios Tzionas
Organizers: Gerard Pons-Moll
This talk presents our 3D video production method by which a user can watch a real game from any free viewpoint. Players in the game are captured by 10 cameras and they are reproduced three dimensionally by billboard based representation in real time. Upon producing the 3D video, we have also worked on good user interface that can enable people move the camera intuitively. As the speaker is also working on wide variety of computer vision to augmented reality, selected recent works will be also introduced briefly.
Dr. Yoshinari Kameda started his research from human pose estimation as his Ph.D thesis, then he expands his interested topics from computer vision, human interface, and augmented reality.
He is now an associate professor at University of Tsukuba.
He is also a member of Center for Computational Science of U-Tsukuba where some outstanding super-computer s are in operation.
He served International Symposium on Mixed and Augmented Reality as a area chair for four years (2007-2010).
3D reconstruction from 2D still-images (Structure-from-Motion) has reached maturity and together with new image acquisition devices like Micro Aerial Vehicles (MAV), new interesting application scenarios arise. However, acquiring an image set which is suited for a complete and accurate reconstruction is even for expert users a non-trivial task. To overcome this problem, we propose two different methods. In the first part of the talk, we will present a SfM method that performs sparse reconstruction of 10Mpx still-images and a surface extraction from sparse and noisy 3D point clouds in real-time. We therefore developed a novel efficient image localisation method and a robust surface extraction that works in a fully incremental manner directly on sparse 3D points without a densification step. The real-time feedback of the reconstruction quality the enables the user to control the acquisition process interactively. In the second part, we will present ongoing work of a novel view planning method that is designed to deliver a set of images that can be processed by today's multi-view reconstruction pipelines.
This talk will highlight recent progress on two fronts. First, we will talk about a novel image-conditioned person model that allows for effective articulated pose estimation in realistic scenarios. Second, we describe our work towards activity recognition and the ability to describe video content with natural language.
Both efforts are part of a longer-term agenda towards visual scene understanding. While visual scene understanding has long been advocated as the "holy grail" of computer vision, we believe it is time to address this challenge again, based on the progress in recent years.
In this talk, I will show that, given probabilities of presence of people at various locations in individual time frames, finding the most likely set of trajectories amounts to solving a linear program that depends on very few parameters.
This can be done without requiring appearance information and in real-time, by using the K-Shortest Paths algorithm (KSP). However, this can result in unwarranted identity switches in complex scenes. In such cases, sparse image information can be used within the Linear Programming framework to keep track of people's identities, even when their paths come close to each other or intersect. By sparse, we mean that the appearance needs only be discriminative in a very limited number of frames, which makes our approach widely applicable.
Manifold learning techniques attempt to map a high-dimensional space onto a lower-dimensional one. From a mathematical point of view, a manifold is a topological Hausdorff space that is locally Euclidean. From Machine Learning point of view, we can interpret this embedded manifold as the underlying support of the data distribution. When dealing with high dimensional data sets, nonlinear dimensionality reduction methods can provide more faithful data representation than linear ones. However, the local geometrical distortion induced by the nonlinear mapping leads to a loss of information and affects interpretability, with a negative impact in the model visualization results.
This talk will discuss an approach which involves probabilistic nonlinear dimensionality reduction through Gaussian Process Latent Variables Models. The main focus is on the intrinsic geometry of the model itself as a tool to improve the exploration of the latent space and to recover information loss due to dimensionality reduction. We aim to analytically quantify and visualize the distortion due to dimensionality reduction in order to improve the performance of the model and to interpret data in a more faithful way.
In collaboration with: N.D. Lawrence (University of Sheffield), A. Vellido (UPC)
Perceptual grouping played a prominent role in support of early object recognition systems, which typically took an input image and a database of shape models and identified which of the models was visible in the image. When the database was large, local features were not sufficiently distinctive to prune down the space of models to a manageable number that could be verified. However, when causally related shape features were grouped, using intermediate-level shape priors, e.g., cotermination, symmetry, and compactness, they formed effective shape indices and allowed databases to grow in size. In recent years, the recognition (categorization) community has focused on the object detection problem, in which the input image is searched for a specific target object. Since indexing is not required to select the target model, perceptual grouping is not required to construct a discriminative shape index; the existence of a much stronger object-level shape prior precludes the need for a weaker intermediate-level shape prior. As a result, perceptual grouping activity at our major conferences has diminished. However, there are clear signs that the recognition community is moving from appearance back to shape, and from detection back to unexpected object recognition. Shape-based perceptual grouping will play a critical role in facilitating this transition. But while causally related features must be grouped, they also need to be abstracted before they can be matched to categorical models. In this talk, I will describe our recent progress on the use of intermediate shape priors in segmenting, grouping, and abstracting shape features. Specifically, I will describe the use of symmetry and non-accidental attachment to detect and group symmetric parts, the use of closure to separate figure from background, and the use of a vocabulary of simple shape models to group and abstract image contours.
This talk presents recent work from CVPR that looks at inference for pairwise CRF models in the highly (or fully) connected case rather than simply a sparse set of neighbours used ubiquitously in many computer vision tasks. Recent work has shown that fully-connected CRFs, where each node is connected to every other node, can be solved very efficiently under the restriction that the pairwise term is a Gaussian kernel over a Euclidean feature space. The method presented generalises this model to allow arbitrary, non-parametric models (which can be learnt from training data and conditioned on test data) to be used for the pairwise potentials. This greatly increases the expressive power of such models whilst maintaining efficient inference.