Applying data-driven approaches to non-rigid 3D reconstruction has been difficult, which we believe can be attributed to the lack of a large-scale training corpus. One recent approach proposes self-supervision based on non-rigid reconstruction. Unfortunately, this method fails for important cases such as highly non-rigid deformations. We first address this problem of lack of data by introducing a novel semi-supervised strategy to obtain dense interframe correspondences from a sparse set of annotations. This way, we obtain a large dataset of 400 scenes, over 390,000 RGB-D frames, and 2,537 densely aligned frame pairs; in addition, we provide a test set along with several metrics for evaluation. Based on this corpus, we introduce a data-driven non-rigid feature matching approach, which we integrate into an optimization-based reconstruction pipeline. Here, we propose a new neural network that operates on RGB-D frames, while maintaining robustness under large non-rigid deformations and producing accurate predictions. Our approach significantly outperforms both existing non-rigid reconstruction methods that do not use learned data terms, as well as learning-based approaches that only use self-supervision.
Organizers: Vassilis Choutas
How can we tell that a video is playing backwards? People's motions look wrong when the video is played backwards--can we develop an algorithm to distinguish forward from backward video? Similarly, can we tell if a video is sped-up? We have developed algorithms to distinguish forwards from backwards video, and fast from slow. Training algorithms for these tasks provides a self-supervised task that facilitates human activity recognition. We'll show these results, and applications of these unsupervised video learning tasks. We also present a method to retime people in videos --- manipulating and editing the time over which the motions of individuals occurs. Our model not only disentangles the motions of each person in the video, but it also correlates each person with the scene changes they generate, and thus re-times the corresponding shadows, reflections, and motion of loose clothing appropriately.
Organizers: Yinghao Huang
In recent years, commodity 3D sensors have become widely available, spawning significant interest in both offline and real-time 3D reconstruction. While state-of-the-art reconstruction results from commodity RGB-D sensors are visually appealing, they are far from usable in practical computer graphics applications since they do not match the high quality of artist-modeled 3D graphics content. One of the biggest challenges in this context is that obtained 3D scans suffer from occlusions, thus resulting in incomplete 3D models. In this talk, I will present a data-driven approach towards generating high quality 3D models from commodity scan data, and the use of these geometrically complete 3D models towards semantic and texture understanding of real-world environments.
Organizers: Yinghao Huang
Vision is a crucial sense for computational systems to interact with their environments as biological systems do. A major task is interpreting images of complex scenes, by recognizing and localizing objects, persons and actions. This involves learning a large number of visual models, ideally autonomously.
In this talk I will present two ways of reducing the amount of human supervision required by this learning process. The first way is labeling images only by the object class they contain. Learning from cluttered images is very challenging in this weakly supervised setting. In the traditional paradigm, each class is learned starting from scratch. In our work instead, knowledge generic over classes is first learned during a meta-training stage from images of diverse classes with given object locations, and is then used to support learning any new class without location annotation. Generic knowledge helps because during meta-training the system can learn about localizing objects in general. As demonstrated experimentally, this approach enables learning from more challenging images than possible before, such as the PASCAL VOC 2007, containing extensive clutter and large scale and appearance variations between object instances.
The second way is the analysis of news items consisting of images and text captions. We associate names and action verbs in the captions to the face and body pose of the persons in the images. We introduce a joint probabilistic model for simultaneously recovering image-caption correspondences and learning appearance models for the face and pose classes occurring in the corpus. As demonstrated experimentally, this joint `face and pose' model solves the correspondence problem better than earlier models covering only the face.
I will conclude with an outlook on the idea of visual culture, where new visual concepts are learned incrementally on top of all visual knowledge acquired so far. Beside generic knowledge, visual culture includes also knowledge specific to a class, knowledge of scene structures and other forms of visual knowledge. Potentially, this approach could considerably extend current visual recognition capabilities and produce an integrated body of visual knowledge.
I will survey our work on tracking and measurement, waypoints on the path to activity recognition and understanding, in sports video, highlighting some of our recent work on rectification and player tracking, not just in hockey but more recently in basketball, where we have addressed player identification both in a fully supervised and semi-supervised manner.
Methods for visual recognition have made dramatic strides in recent years on various online benchmarks, but performance in the real world still often falters. Classic gradient-histogram models make overly simplistic assumptions regarding image appearance statistics, both locally and globally. Recent progress suggests that new learning-based representations can improve recognition by devices that are embedded in a physical world.
I'll review new methods for domain adaptation which capture the visual domain shift between environments, and improve recognition of objects in specific places when trained from generic online sources. I'll discuss methods for cross-modal semi-supervised learning, which can leverage additional unlabeled modalities in a test environment.
Finally as time permits I'll present recent results learning hierarchical local image representations based on recursive probabilistic topic models, on learning strong object color models from sets of uncalibrated views using a new multi-view color constancy paradigm, and/or on recent results on monocular estimation of grasp affordances.
In the first part of the talk, I will describe methods that learn a single family of detectors for object classes that exhibit large within-class variation. One common solution is to use a divide-and-conquer strategy, where the space of possible within-class variations is partitioned, and different detectors are trained for different partitions.
However, these discrete partitions tend to be arbitrary in continuous spaces, and the classifiers have limited power when there are too few training samples in each subclass. To address this shortcoming, explicit feature sharing has been proposed, but it also makes training more expensive. We show that foreground-background classification (detection) and within-class classification of the foreground class (pose estimation) can be jointly solved in a multiplicative form of two kernel functions. One kernel measures similarity for foreground-background classification. The other kernel accounts for latent factors that control within-class variation and implicitly enables feature sharing among foreground training samples. The multiplicative kernel formulation enables feature sharing implicitly; the solution for the optimal sharing is a byproduct of SVM learning.
The resulting detector family is tuned to specific variations in the foreground. The effectiveness of this framework is demonstrated in experiments that involve detection, tracking, and pose estimation of human hands, faces, and vehicles in video.
Beginning with a seminal paper of Diaconis (1988), the aim of so-called "probabilistic numerics" is to compute probabilistic solutions to deterministic problems arising in numerical analysis by casting them as statistical inference problems. For example, numerical integration of a deterministic function can be seen as the integration of an unknown/random function, with evaluations of the integrand at the integration nodes proving partial information about the integrand. Advantages offered by this viewpoint include: access to the Bayesian representation of prior and posterior uncertainties; better propagation of uncertainty through hierarchical systems than simple worst-case error bounds; and appropriate accounting for numerical truncation and round-off error in inverse problems, so that the replicability of deterministic simulations is not confused with their accuracy, thereby yielding an inappropriately concentrated Bayesian posterior. This talk will describe recent work on probabilistic numerical solvers for ordinary and partial differential equations, including their theoretical construction, convergence rates, and applications to forward and inverse problems. Joint work with Andrew Stuart (Warwick).
Organizers: Philipp Hennig