We consider a new problem of adapting a human mesh reconstruction model to out-of-domain streaming videos, where the performance of existing SMPL-based models is significantly affected by the distribution shift represented by different camera parameters, bone lengths, backgrounds, and occlusions. We tackle this problem through online adaptation, gradually correcting the model bias during testing. There are two main challenges: First, the lack of 3D annotations increases the training difficulty and results in 3D ambiguities. Second, non-stationary data distribution makes it difficult to strike a balance between fitting regular frames and hard samples with severe occlusions or dramatic changes. To this end, we propose the Dynamic Bilevel Online Adaptation algorithm (DynaBOA). It first introduces the temporal constraints to compensate for the unavailable 3D annotations and leverages a bilevel optimization procedure to address the conflicts between multi-objectives. DynaBOA provides additional 3D guidance by co-training with similar source examples retrieved efficiently despite the distribution shift. Furthermore, it can adaptively adjust the number of optimization steps on individual frames to fully fit hard samples and avoid overfitting regular frames. DynaBOA achieves state-of-the-art results on three out-of-domain human mesh reconstruction benchmarks.

This paper considers a new problem of adapting a pretrained model of human mesh reconstruction to out-of-domain streaming videos. However, most previous methods based on the parametric SMPL model [36] underperform in new domains with unexpected, domain-specific attributes, such as camera parameters, lengths of bones, backgrounds, and occlusions. Our general idea is to dynamically fine-tune the source model on test video streams with additional temporal constraints, such that it can mitigate the domain gaps without over-fitting the 2D information of individual test frames. A subsequent challenge is how to avoid conflicts between the 2D and temporal constraints. We propose to tackle this problem using a new training algorithm named Bilevel Online Adaptation (BOA), which divides the optimization process of overall multi-objective into two steps of weight probe and weight update in a training iteration. We demonstrate that BOA leads to state-of-the-art results on two human mesh reconstruction benchmarks1.

Synthesizing 3D human motion plays an important role in many graphics applications as well as understanding human activity. While many efforts have been made on generating realistic and natural human motion, most approaches neglect the importance of modeling human-scene interactions and affordance. On the other hand, affordance reasoning (e.g., standing on the floor or sitting on the chair) has mainly been studied with static human pose and gestures, and it has rarely been addressed with human motion. In this paper, we propose to bridge human motion synthesis and scene affordance reasoning. We present a hierarchical generative framework to synthesize long-term 3D human motion conditioning on the 3D scene structure. Building on this framework, we further enforce multiple geometry constraints between the human mesh and scene point clouds via optimization to improve realistic synthesis. Our experiments show significant improvements over previous approaches on generating natural and physically plausible human motion in a scene.1

In this work, we study the ambiguity problem in the task of unsupervised 3D human pose estimation from 2D counterpart. On one hand, without explicit annotation, the scale of 3D pose is difficult to be accurately captured (scale ambiguity). On the other hand, one 2D pose might correspond to multiple 3D gestures, where the lifting procedure is inherently ambiguous (pose ambiguity). Previous methods generally use temporal constraints (e.g., constant bone length and motion smoothness) to alleviate the above issues. However, these methods commonly enforce the outputs to fulfill multiple training objectives simultaneously, which often lead to sub-optimal results. In contrast to the majority of previous works, we propose to split the whole problem into two sub-tasks, i.e., optimizing 2D input poses via a scale estimation module and then mapping optimized 2D pose to 3D counterpart via a pose lifting module. Furthermore, two temporal constraints are proposed to alleviate the scale and pose ambiguity respectively. These two modules are optimized via a iterative training scheme with corresponding temporal constraints, which effectively reduce the learning difficulty and lead to better performance. Results on the Human3.6M dataset demonstrate that our approach improves upon the prior art by 23.1% and also outperforms several weakly supervised approaches that rely on 3D annotations. Our project is available at https://sites.google.com/view/ambiguity-aware-hpe.

In this paper, we decouple unsupervised human mesh recovery into the well-studied problems of unsupervised 3D pose estimation, and human mesh recovery from estimated 3D skeletons, focusing on the latter task. The challenges of the latter task are two folds: (1) pose failure (i.e., pose mismatching – different skeleton definitions in dataset and SMPL , and pose ambiguity – endpoints have arbitrary joint angle configurations for the same 3D joint coordinates). (2) shape ambiguity (i.e., the lack of shape constraints on body configuration). To address these issues, we propose Skeleton2Mesh, a novel lightweight framework that recovers human mesh from a single image. Our Skeleton2Mesh contains three modules, i.e., Differentiable Inverse Kinematics (DIK), Pose Refinement (PR) and Shape Refinement (SR) modules. DIK is designed to transfer 3D rotation from estimated 3D skeletons, which relies on a minimal set of kinematics prior knowledge. Then PR and SR modules are utilized to tackle the pose ambiguity and shape ambiguity respectively. All three modules can be incorporated into Skeleton2Mesh seamlessly via an end-to-end manner. Furthermore, we utilize an adaptive joint regressor to alleviate the effects of skeletal topology from different datasets. Results on the Human3.6M dataset for human mesh recovery demonstrate that our method improves upon the previous unsupervised methods by 32.6% under the same setting. Qualitative results on in-the-wild datasets exhibit that the recovered 3D meshes are natural, realistic. Our project is available at https://sites.google.com/view/skeleton2mesh.

With the increased availability of rich tactile sensors, there is an an equally proportional need for open-source and integrated software capable of efficiently and effectively processing raw touch measurements into high-level signals that can be used for control and decision-making. In this paper, we present PyTouch – the first machine learning library dedicated to the processing of touch sensing signals. PyTouch, is designed to be modular, easy-to-use and provides state-of-the-art touch processing capabilities as a service with the goal of unifying the tactile sensing community by providing a library for building scalable, proven, and performance-validated modules over which applications and research can be built upon. We evaluate PyTouch on real-world data from several tactile sensors on touch processing tasks such as touch detection, slip and object pose estimations. PyTouch is open-sourced at https://github.com/facebookresearch/pytouch.

There have been considerable debates over 2D and 3D representation learning on 3D medical images. 2D approaches could benefit from large-scale 2D pretraining, whereas they are generally weak in capturing large 3D contexts. 3D approaches are natively strong in 3D contexts, however few publicly available 3D medical dataset is large and diverse enough for universal 3D pretraining. Even for hybrid (2D + 3D) approaches, the intrinsic disadvantages within the 2D/3D parts still exist. In this study, we bridge the gap between 2D and 3D convolutions by reinventing the 2D convolutions. We propose ACS (axial-coronal-sagittal) convolutions to perform natively 3D representation learning, while utilizing the pretrained weights on 2D datasets. In ACS convolutions, 2D convolution kernels are split by channel into three parts, and convoluted separately on the three views (axial, coronal and sagittal) of 3D representations. Theoretically, ANY 2D CNN (ResNet, DenseNet, or DeepLab) is able to be converted into a 3D ACS CNN, with pretrained weight of a same parameter size. Extensive experiments validate the consistent superiority of the pretrained ACS CNNs, over the 2D/3D CNN counterparts with/without pretraining. Even without pretraining, the ACS convolution can be used as a plug-and-play replacement of standard 3D convolution, with smaller model size and less computation.

For monocular 3D pose estimation conditioned on 2D detection, noisy/unreliable input is a key obstacle in this task. Simple structure constraints attempting to tackle this problem, e.g., symmetry loss and joint angle limit, could only provide marginal improvements and are commonly treated as auxiliary losses in previous researches. Thus it still remains challenging about how to effectively utilize the power of human prior knowledge for this task. In this paper, we propose to address above issue in a systematic view. Firstly, we show that optimizing the kinematics structure of noisy 2D inputs is critical to obtain accurate 3D estimations. Secondly, based on corrected 2D joints, we further explicitly decompose articulated motion with human topology, which leads to more compact 3D static structure easier for estimation. Finally, temporal refinement emphasizing the validity of 3D dynamic structure is naturally developed to pursue more accurate result. Above three steps are seamlessly integrated into deep neural models, which form a deep kinematics analysis pipeline concurrently considering the static/dynamic structure of 2D inputs and 3D outputs. Extensive experiments show that proposed framework achieves state-of-the-art performance on two widely used 3D human action datasets. Meanwhile, targeted ablation study shows that each former step is critical for the latter one to obtain promising results.

In video prediction tasks, one major challenge is to capture the multi-modal nature of future contents and dynamics. In this work, we propose a simple yet effective framework that can efficiently predict plausible future states, where the key insight is that the potential distribution of a sequence could be approximated with analogous ones in a repertoire of training pool, namely, expert examples. By further incorporating a novel optimization scheme into the training procedure, plausible predictions can be sampled efficiently from distribution constructed from the retrieved examples. Meanwhile, our method could be seamlessly integrated with existing stochastic predictive models; significant enhancement is observed with comprehensive experiments in both quantitative and qualitative aspects. We also demonstrate the generalization ability to predict the motion of unseen class, i.e., without access to corresponding data during training phase. Project Page: \hyperlink{https://sites.google.com/view/vpeg-supp/home.}{https://sites.google.com/view/vpeg-supp/home.}

Video generation is a challenging task due to the extremely high-dimensional distribution of the solution space. Good constraints in the solution domain would thus reduce the difficulty of approximating optimal solutions. In this paper, instead of directly generating high-dimensional video data, we propose using object landmarks as explicit structure constraints to address this issue. Specifically, we propose a two-stage framework for an action-conditioned video generation task. In our framework, the first stage aims to generate landmark sequences according to predefined motion types, and a recurrent model (RNN/LSTM) is adopted for this purpose. The landmark sequence can be regarded as a low-dimensional structure embedding of high-dimensional video data, and generating landmark sequences is much easier than generating videos. The second stage is inspired by a conditional generative adversarial network (CGAN), and we take the generated landmark sequence as a structure condition to learn a landmark-to-image translation network. Such a one-to-one translation framework avoids the difficulty of generating videos and instead transfers the video generation task to image generation, which is resolvable due to the maturity of current GAN-based models. The experimental results demonstrate that our model not only achieves promising results on rigid/nonrigid motion generation tasks but also can be extended to multiobject motion situations.

Despite recent emergence of adversarial based methods for video prediction, existing algorithms often produce unsatisfied results in image regions with rich structural information (i.e., object boundary) and detailed motion (i.e., articulated body movement). To this end, we present a structure preserving video prediction framework to explicitly address above issues and enhance video prediction quality. On one hand, our framework contains a two-stream generation architecture which deals with high frequency video content (i.e., detailed object or articulated motion structure) and low frequency video content (i.e., location or moving directions) in two separate streams. On the other hand, we propose a RNN structure for video prediction, which employs temporal-adaptive convolutional kernels to capture time-varying motion patterns as well as tiny objects within a scene. Extensive experiments on diverse scenes, ranging from human motion to semantic layout prediction, demonstrate the effectiveness of the proposed video prediction approach.

We aim to automatically generate human motion sequence from a single input person image, with some specific action label. To this end, we propose a cross-space human motion video generation network which features two paths: a forward path that first samples/generates a sequence of low dimensional motion vectors based on Gaussian Process (GP), which is paired with the input person image to form a moving human figure sequence; and a backward path based on the predicted human images to re-extract the corresponding latent motion representations. As lack of supervision, the reconstructed latent motion representations are expected to be as close as possible to the GP sampled ones, thus yielding a cyclic objective function for cross-space (i.e., motion and appearance) mutual constrained generation. We further propose an alternative sampling/generation algorithm with respect to constraints from both spaces. Extensive experimental results show that the proposed framework successfully generates novel human motion sequences with reasonable visual quality.

Key to automatically generate natural scene images is to properly arrange amongst various spatial elements, especially in the depth cue. To this end, we introduce a novel depth structure preserving scene image generation network (DSP-GAN), which favors a hierarchical architecture, for the purpose of depth structure preserving scene image generation. The main trunk of the proposed infrastructure is built upon a Hawkes point process that models high-order spatial dependency between different depth layers. Within each layer generative adversarial sub-networks are trained collaboratively to generate realistic scene components, conditioned on the layer information produced by the point process. We experiment our model on annotated natural scene images collected from SUN dataset and demonstrate that our models are capable of generating depth-realistic natural scene image.

Most adversarial learning based video prediction methods suffer from image blur, since the commonly used adversarial and regression loss pair work rather in a competitive way than collaboration, yielding compromised blur effect. In the meantime, as often relying on a single-pass architecture, the predictor is inadequate to explicitly capture the forthcoming uncertainty. Our work involves two key insights: (1) Video prediction can be approached as a stochastic process: we sample a collection of proposals conforming to possible frame distribution at following time stamp, and one can select the final prediction from it. (2) De-coupling combined loss functions into dedicatedly designed sub-networks encourages them to work in a collaborative way. Combining above two insights we propose a two-stage network called VPSS (\textbf{V}ideo \textbf{P}rediction via \textbf{S}elective \textbf{S}ampling). Specifically a \emph{Sampling} module produces a collection of high quality proposals, facilitated by a multiple choice adversarial learning scheme, yielding diverse frame proposal set. Subsequently a \emph{Selection} module selects high possibility candidates from proposals and combines them to produce final prediction. Extensive experiments on diverse challenging datasets demonstrate the effectiveness of proposed video prediction approach, i.e., yielding more diverse proposals and accurate prediction results.

This work makes the first attempt to generate articulated human motion sequence from a single image. On one hand, we utilize paired inputs including human skeleton information as motion embedding and a single human image as appearance reference, to generate novel motion frames based on the conditional GAN infrastructure. On the other hand, a triplet loss is employed to pursue appearance smoothness between consecutive frames. As the proposed framework is capable of jointly exploiting the image appearance space and articulated/kinematic motion space, it generates realistic articulated motion sequence, in contrast to most previous video generation methods which yield blurred motion effects. We test our model on two human action datasets including KTH and Human3.6M, and the proposed framework generates very promising results on both datasets.