Motion capture from a monocular video is fundamental and crucial for us humans to naturally experience and interact with each other in Virtual Reality (VR) and Augmented Reality (AR). However, existing methods still struggle with challenging cases involving self-occlusion and complex poses due to the lack of effective motion prior modeling. In this paper, we present a novel variational motion prior (VMP) learning approach for video-based motion capture to resolve the above issue. Instead of directly building the correspondence between the video and motion domain, We propose to learn a generic latent space for capturing the prior distribution of all natural motions, which serve as the basis for subsequent video-based motion capture tasks. To improve the generalization capacity of prior space, we propose a transformer-based variational autoencoder pretrained over marker-based 3D mocap data, with a novel style-mapping block to boost the generation quality. Afterward, a separate video encoder is attached to the pretrained motion generator for end-to-end fine-tuning over task-specific video datasets. Compared to existing motion prior models, our VMP model serves as a motion rectifier that can effectively reduce temporal jittering and failure modes in frame-wise pose estimation, leading to temporally stable and visually realistic motion capture results. Furthermore, our VMP-based framework models motion at sequence level and can directly generate motion clips in the forward pass, achieving real-time motion capture during inference. Extensive experiments over both public datasets and in-the-wild videos have demonstrated the efficacy and generalization capability of our framework.
The use of latent variable models has shown to be a powerful tool for modeling probability distributions over sequences. In this paper, we introduce a new variational model that extends the recurrent network in two ways for the task of video frame prediction. First, we introduce 3D convolutions inside all modules including the recurrent model for future frame prediction, inputting and outputting a sequence of video frames at each timestep. This enables us to better exploit spatiotemporal information inside the variational recurrent model, allowing us to generate high-quality predictions. Secon…
IIIT Delhi（德里印度理工学院）；Bioinformatics Institute, A*STAR（A*STAR生物信息研究所）；Singapore University of Technology and Design（新加坡科技设计大学）
We introduce MGP-VAE (Multi-disentangled-features Gaussian Processes Variational AutoEncoder), a variational autoencoder which uses Gaussian processes (GP) to model the latent space for the unsupervised learning of disentangled representations in video sequences. We improve upon previous work by establishing a framework by which multiple features, static or dynamic, can be disentangled. Specifically we use fractional Brownian motions (fBM) and Brownian bridges (BB) to enforce an inter-frame correlation structure in each independent channel, and show that varying this structure enables one to c…
Indian Institute of Technology Kanpur（印度理工学院坎普尔分校）；NVIDIA（英伟达）；University of Bath（巴斯大学）
Understanding the relationship between the auditory and visual signals is crucial for many different applications ranging from computer-generated imagery (CGI) and video editing automation to assisting people with hearing or visual impairments. However, this is challenging since the distribution of both audio and visual modality is inherently multimodal. Therefore, most of the existing methods ignore the multimodal aspect and assume that there only exists a deterministic one-to-one mapping between the two modalities. It can lead to low-quality predictions as the model collapses to optimizing t…
The Chinese University of Hong Kong (CUHK)（香港中文大学（CUHK））
To synthesize a realistic action sequence based on a single human image, it is crucial to model both motion patterns and diversity in the action video. This paper proposes an Action Conditional Temporal Variational AutoEncoder (ACT-VAE) to improve motion prediction accuracy and capture movement diversity. ACT-VAE predicts pose sequences for an action clips from a single input image. It is implemented as a deep generative model that maintains temporal coherence according to the action category with a novel temporal modeling on latent space. Further, ACT-VAE is a general action sequence predicti…
University of Science Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）
Predicting future frames of video sequences is challenging due to the complex and stochastic nature of the problem. Video prediction methods based on variational auto-encoders (VAEs) have been a great success, but they require the training data to contain multiple possible futures for an observed video sequence. This is hard to be fulfilled when videos are captured in the wild where any given observation only has a determinate future. As a result, training a vanilla VAE model with these videos inevitably causes posterior collapse. To alleviate this problem, we propose a novel VAE structure, da…
Spiking Variational Graph Representation Inference for Video Summarization
Department of Computer Science and Technology, Harbin Institute of Technology（计算机科学与技术系，哈尔滨工业大学）；Harbin Institute of Technology Suzhou Research Institute（哈尔滨工业大学苏州研究 institute）；School of mathmatical Sciences/Multi-Hazard Early Warning Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China（数学科学学院/四川省多灾种早期预警重点实验室，电子科技大学）；School of Electronic Engineering and Computer Science, Institute of Digital Media, Peking University（电子工程与计算机科学系，数字媒体研究院，北京大学）
Video anomalies detection is the intersection of anomaly detection and visual intelligence. It has commercial applications in surveillance, security, self-driving cars and crop monitoring. Videos can capture a variety of anomalies. Due to efforts needed to label training data, unsupervised approaches to train anomaly detection models for videos is more practical An autoencoder is a neural network that is trained to recreate its input using latent representation of input also called a bottleneck layer. Variational autoencoder uses distribution (mean and variance) as compared to latent vector as…
This paper proposes a method for performing continual learning of predictive models that facilitate the inference of future frames in video sequences. For a first given experience, an initial Variational Autoencoder, together with a set of fully connected neural networks are utilized to respectively learn the appearance of video frames and their dynamics at the latent space level. By employing an adapted Markov Jump Particle Filter, the proposed method recognizes new situations and integrates them as predictive models avoiding catastrophic forgetting of previously learned tasks. For evaluating…
We present a novel end-to-end partially supervised deep learning approach for video anomaly detection and localization using only normal samples. The insight that motivates this study is that the normal samples can be associated with at least one Gaussian component of a Gaussian Mixture Model (GMM), while anomalies either do not belong to any Gaussian component. The method is based on Gaussian Mixture Variational Autoencoder, which can learn feature representations of the normal samples as a Gaussian Mixture Model trained using deep learning. A Fully Convolutional Network (FCN) that does not c…
State Key Lab of CAD&CG, Zhejiang University（浙江大学计算机辅助设计与图形学国家重点实验室）；Zhejiang Lab（之江实验室）
Recent advances in image-based human pose estimation make it possible to capture 3D human motion from a single RGB video. However, the inherent depth ambiguity and self-occlusion in a single view prohibit the recovery of as high-quality motion as multi-view reconstruction. While multi-view videos are not common, the videos of a celebrity performing a specific action are usually abundant on the Internet. Even if these videos were recorded at different time instances, they would encode the same motion characteristics of the person. Therefore, we propose to capture human motion by jointly analyzi…
As an emerging type of user-generated content, micro-video drastically enriches people's entertainment experiences and social interactions. However, the popularity pattern of an individual micro-video still remains elusive among the researchers. One of the major challenges is that the potential popularity of a micro-video tends to fluctuate under the impact of various external factors, which makes it full of uncertainties. In addition, since micro-videos are mainly uploaded by individuals that lack professional techniques, multiple types of noise could exist that obscure useful information. In…
Gaussian Process Prior Variational Autoencoder for Endoscopic Videos
Department of Electromechanics, InViLab, University of Antwerp（安特卫普大学机电工程系InViLab实验室）；Department of Computer Science, University of Manchester（曼彻斯特大学计算机科学系）；Department of Electrical Engineering, Eindhoven University of Technology（埃因霍温理工大学电气工程系）
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of California, Berkeley（加州大学伯克利分校）；Google Brain（谷歌大脑）
Predicting the future in real-world settings, particularly from raw sensory observations such as images, is exceptionally challenging. Real-world events can be stochastic and unpredictable, and the high dimensionality and complexity of natural images requires the predictive model to build an intricate understanding of the natural world. Many existing methods tackle this problem by making simplifying assumptions about the environment. One common assumption is that the outcome is deterministic and there is only one plausible future. This can lead to low-quality predictions in real-world settings…
Georgia Institute of Technology（佐治亚理工学院）；ETH Zürich（苏黎世联邦理工学院）；Zhejiang University（浙江大学）
We introduce a novel task of reconstructing a time series of second-person 3D human body meshes from monocular egocentric videos. The unique viewpoint and rapid embodied camera motion of egocentric videos raise additional technical barriers for human body capture. To address those challenges, we propose a simple yet effective optimization-based approach that leverages 2D observations of the entire video sequence and human-scene interaction constraint to estimate second-person human poses, shapes, and global motion that are grounded on the 3D environment captured from the egocentric view. We co…
University of Erlangen-Nuremberg（埃尔朗根-纽伦堡大学）；Max-Planck-Institute for Informatics（马克斯·普朗克信息学研究所）；Stanford University（斯坦福大学）
We present Face2Face, a novel approach for real-time facial reenactment of a monocular target video sequence (e.g., Youtube video). The source sequence is also a monocular video stream, captured live with a commodity webcam. Our goal is to animate the facial expressions of the target video by a source actor and re-render the manipulated output video in a photo-realistic fashion. To this end, we first address the under-constrained problem of facial identity recovery from monocular video by non-rigid model-based bundling. At run time, we track facial expressions of both source and target video u…
Data and Web Science Group, University of Mannheim（曼海姆大学数据与网络科学组）；Fraunhofer ITWM, Competence Center HPC（弗劳恩霍夫工业数学研究所高性能计算能力中心）；Fraunhofer Center Machine Learning（弗劳恩霍夫机器学习中心）；Mathematical Image Analysis Group, Saarland University（萨尔大学数学图像分析组）
We propose a light-weight variational framework for online tracking of object segmentations in videos based on optical flow and image boundaries. While high-end computer vision methods on this task rely on sequence specific training of dedicated CNN architectures, we show the potential of a variational model, based on generic video information from motion and color. Such cues are usually required for tasks such as robot navigation or grasp estimation. We leverage them directly for video object segmentation and thus provide accurate segmentations at potentially very low extra cost. Our simple m…
University of Toronto（多伦多大学）；Google Research, Brain Team（谷歌研究院大脑团队）
Deep learning has enabled algorithms to generate realistic images. However, accurately predicting long video sequences requires understanding long-term dependencies and remains an open challenge. While existing video prediction models succeed at generating sharp images, they tend to fail at accurately predicting far into the future. We introduce the Clockwork VAE (CW-VAE), a video prediction model that leverages a hierarchy of latent sequences, where higher levels tick at slower intervals. We demonstrate the benefits of both hierarchical latents and temporal abstraction on 4 diverse video pred…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Mitsubishi Electric Research Laboratories（三菱电机研究实验室）
Predicting the future frames of a video is a challenging task, in part due to the underlying stochastic real-world phenomena. Prior approaches to solve this task typically estimate a latent prior characterizing this stochasticity, however do not account for the predictive uncertainty of the (deep learning) model. Such approaches often derive the training signal from the mean-squared error (MSE) between the generated frame and the ground truth, which can lead to sub-optimal training, especially when the predictive uncertainty is high. Towards this end, we introduce Neural Uncertainty Quantifier…
While describing Spatio-temporal events in natural language, video captioning models mostly rely on the encoder's latent visual representation. Recent progress on the encoder-decoder model attends encoder features mainly in linear interaction with the decoder. However, growing model complexity for visual data encourages more explicit feature interaction for fine-grained information, which is currently absent in the video captioning domain. Moreover, feature aggregations methods have been used to unveil richer visual representation, either by the concatenation or using a linear layer. Though fe…
A video prediction model that generalizes to diverse scenes would enable intelligent agents such as robots to perform a variety of tasks via planning with the model. However, while existing video prediction models have produced promising results on small datasets, they suffer from severe underfitting when trained on large and diverse datasets. To address this underfitting challenge, we first observe that the ability to train larger video prediction models is often bottlenecked by the memory constraints of GPUs or TPUs. In parallel, deep hierarchical latent variable models can produce higher qu…
ETH Zürich（苏黎世联邦理工学院）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
Capturing the dynamically deforming 3D shape of clothed human is essential for numerous applications, including VR/AR, autonomous driving, and human-computer interaction. Existing methods either require a highly specialized capturing setup, such as expensive multi-view imaging systems, or they lack robustness to challenging body poses. In this work, we propose a method capable of capturing the dynamic 3D human shape from a monocular video featuring challenging body poses, without any additional input. We first build a 3D template human model of the subject based on a learned regression model. …
CANeRV: Content Adaptive Neural Representation for Video Compression
School of Computer Science and Technology, University of Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院）；Bytedance Inc.（字节跳动公司）；School of Computer Science, Peking University（北京大学计算机学院）
Tsinghua University（清华大学）；The University of Hong Kong（香港大学）
We introduce MulayCap, a novel human performance capture method using a monocular video camera without the need for pre-scanning. The method uses "multi-layer" representations for geometry reconstruction and texture rendering, respectively. For geometry reconstruction, we decompose the clothed human into multiple geometry layers, namely a body mesh layer and a garment piece layer. The key technique behind is a Garment-from-Video (GfV) method for optimizing the garment shape and reconstructing the dynamic cloth to fit the input video sequence, based on a cloth simulation model which is effectiv…
Zhejiang University（浙江大学）；University of Technology Sydney（悉尼科技大学）；University of California, Santa Cruz（加州大学圣克鲁兹分校）
Temporal grounding in videos aims to localize one target video segment that semantically corresponds to a given query sentence. Thanks to the semantic diversity of natural language descriptions, temporal grounding allows activity grounding beyond pre-defined classes and has received increasing attention in recent years. The semantic diversity is rooted in the principle of compositionality in linguistics, where novel semantics can be systematically described by combining known words in novel ways (compositional generalization). However, current temporal grounding datasets do not specifically te…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Stanford University（斯坦福大学）
We present the first real-time human performance capture approach that reconstructs dense, space-time coherent deforming geometry of entire humans in general everyday clothing from just a single RGB video. We propose a novel two-stage analysis-by-synthesis optimization whose formulation and implementation are designed for high performance. In the first stage, a skinned template model is jointly fitted to background subtracted input video, 2D and 3D skeleton joint positions found using a deep neural network, and a set of sparse facial landmark detections. In the second stage, dense non-rigid 3D…
Institute for Brain and Cognitive Sciences, Tsinghua University（清华大学脑与认知科学研究院）；Tianjin University（天津大学）
This paper contributes a novel realtime multi-person motion capture algorithm using multiview video inputs. Due to the heavy occlusions in each view, joint optimization on the multiview images and multiple temporal frames is indispensable, which brings up the essential challenge of realtime efficiency. To this end, for the first time, we unify per-view parsing, cross-view matching, and temporal tracking into a single optimization framework, i.e., a 4D association graph that each dimension (image space, viewpoint and time) can be treated equally and simultaneously. To solve the 4D association g…
STS-Mixer: Spatio-Temporal-Spectral Mixer for 4D Point Cloud Video Understanding
Nanyang Technological University（南洋理工大学）；Alibaba Group（阿里巴巴集团）；Zhejiang University of Technology（浙江工业大学）；University of Chinese Academy of Sciences（中国科学院大学）
Institute of Computer Science and Technology, Peking University（北京大学计算机科学技术研究所）
Video captioning aims to automatically generate natural language descriptions of video content, which has drawn a lot of attention recent years. Generating accurate and fine-grained captions needs to not only understand the global content of video, but also capture the detailed object information. Meanwhile, video representations have great impact on the quality of generated captions. Thus, it is important for video captioning to capture salient objects with their detailed temporal dynamics, and represent them using discriminative spatio-temporal representations. In this paper, we propose a ne…
ShanghaiTech University（上海科技大学）；Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences（中国科学院上海微系统与信息技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Huazhong University of Science and Technology（华中科技大学）
Markerless motion capture and understanding of professional non-daily human movements is an important yet unsolved task, which suffers from complex motion patterns and severe self-occlusion, especially for the monocular setting. In this paper, we propose SportsCap -- the first approach for simultaneously capturing 3D human motions and understanding fine-grained actions from monocular challenging sports video input. Our approach utilizes the semantic and temporally structured sub-motion prior in the embedding space for motion capture and understanding in a data-driven multi-task manner. To enab…
FlowHMR: Physically Plausible Motion Capture from Video
Peking University（北京大学）；The Hong Kong University of Science and Technology（香港科技大学）；Tencent（腾讯）；East China Normal University（华东师范大学）；Sun Yat-sen University（中山大学）；Zhejiang University（浙江大学）
We present SlowFast networks for video recognition. Our model involves (i) a Slow pathway, operating at low frame rate, to capture spatial semantics, and (ii) a Fast pathway, operating at high frame rate, to capture motion at fine temporal resolution. The Fast pathway can be made very lightweight by reducing its channel capacity, yet can learn useful temporal information for video recognition. Our models achieve strong performance for both action classification and detection in video, and large improvements are pin-pointed as contributions by our SlowFast concept. We report state-of-the-art ac…
What's the most accurate 3D model of your face you can obtain while sitting at your desk? We attempt to answer this question in our work. High fidelity face reconstructions have so far been limited to either studio settings or through expensive 3D scanners. On the other hand, unconstrained reconstruction methods are typically limited by low-capacity models. Our method reconstructs accurate face geometry of a subject using a video shot from a smartphone in an unconstrained environment. Our approach takes advantage of recent advances in visual SLAM, keypoint detection, and object detection to im…
Institute of Information Science, Academia Sinica（中央研究院资讯科学研究所）；Providence University（静宜大学）
Learning to capture human motion is essential to 3D human pose and shape estimation from monocular video. However, the existing methods mainly rely on recurrent or convolutional operation to model such temporal information, which limits the ability to capture non-local context relations of human motion. To address this problem, we propose a motion pose and shape network (MPS-Net) to effectively capture humans in motion to estimate accurate and temporally coherent 3D human pose and shape from a video. Specifically, we first propose a motion continuity attention (MoCA) module that leverages visu…
Video capture is the most extensively utilized human perception source due to its intuitively understandable nature. A desired video capture often requires multiple environmental conditions such as ample ambient-light, unobstructed space, and proper camera angle. In contrast, wireless measurements are more ubiquitous and have fewer environmental constraints. In this paper, we propose CSI2Video, a novel cross-modal method that leverages only WiFi signals from commercial devices and a source of human identity information to recover fine-grained surveillance video in a real-time manner. Specifica…
