This paper introduces an unsupervised framework to extract semantically rich features for video representation. Inspired by how the human visual system groups objects based on motion cues, we propose a deep convolutional neural network that disentangles motion, foreground and background information. The proposed architecture consists of a 3D convolutional feature encoder for blocks of 16 frames, which is trained for reconstruction tasks over the first and last frames of the sequence. A preliminary supervised experiment was conducted to verify the feasibility of proposed method by training the model with a fraction of videos from the UCF-101 dataset taking as ground truth the bounding boxes around the activity regions. Qualitative results indicate that the network can successfully segment foreground and background in videos as well as update the foreground appearance based on disentangled motion features. The benefits of these learned features are shown in a discriminative classification task, where initializing the network with the proposed pretraining method outperforms both random initialization and autoencoder pretraining. Our model and source code are publicly available at https://imatge-upc.github.io/unsupervised-2017-cvprw/ .
We propose an unsupervised variational model for disentangling video into independent factors, i.e. each factor's future can be predicted from its past without considering the others. We show that our approach often learns factors which are interpretable as objects in a scene.
Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡大学）；University of Engineering and Technology, Vietnam National University, Hanoi（越南国立大学河内工程技术大学）
In the context of online Robust Principle Component Analysis (RPCA) for the video foreground-background separation, we propose a compressive online RPCA with optical flow that separates recursively a sequence of frames into sparse (foreground) and low-rank (background) components. Our method considers a small set of measurements taken per data vector (frame), which is different from conventional batch RPCA, processing all the data directly. The proposed method also incorporates multiple prior information, namely previous foreground and background frames, to improve the separation and then upda…
Recently, video-based person re-identification (re-ID) has drawn increasing attention in compute vision community because of its practical application prospects. Due to the inaccurate person detections and pose changes, pedestrian misalignment significantly increases the difficulty of feature extraction and matching. To address this problem, in this paper, we propose a \textbf{R}eference-\textbf{A}ided \textbf{P}art-\textbf{A}ligned (\textbf{RAPA}) framework to disentangle robust features of different parts. Firstly, in order to obtain better references between different videos, a pose-based r…
In video data, busy motion details from moving regions are conveyed within a specific frequency bandwidth in the frequency domain. Meanwhile, the rest of the frequencies of video data are encoded with quiet information with substantial redundancy, which causes low processing efficiency in existing video models that take as input raw RGB frames. In this paper, we consider allocating intenser computation for the processing of the important busy information and less computation for that of the quiet information. We design a trainable Motion Band-Pass Module (MBPM) for separating busy information …
Indian Institute of Technology, Madras（马德拉斯印度理工学院）
Video generation is a challenging task that requires modeling plausible spatial and temporal dynamics in a video. Inspired by how humans perceive a video by grouping a scene into moving and stationary components, we propose a method that decomposes the task of video generation into the synthesis of foreground, background and motion. Foreground and background together describe the appearance, whereas motion specifies how the foreground moves in a video over time. We propose V3GAN, a novel three-branch generative adversarial network where two branches model foreground and background information,…
We consider the problem of providing dense segmentation masks for object discovery in videos. We formulate the object discovery problem as foreground motion clustering, where the goal is to cluster foreground pixels in videos into different objects. We introduce a novel pixel-trajectory recurrent neural network that learns feature embeddings of foreground pixel trajectories linked across time. By clustering the pixel trajectories using the learned feature embeddings, our method establishes correspondences between foreground object masks across video frames. To demonstrate the effectiveness of …
EDF R&D（法国电力集团研发中心）；CEDRIC, Conservatoire National des Arts et Métiers（法国国立工艺学院CEDRIC实验室）
Leveraging physical knowledge described by partial differential equations (PDEs) is an appealing way to improve unsupervised video prediction methods. Since physics is too restrictive for describing the full visual content of generic videos, we introduce PhyDNet, a two-branch deep architecture, which explicitly disentangles PDE dynamics from unknown complementary information. A second contribution is to propose a new recurrent physical cell (PhyCell), inspired from data assimilation techniques, for performing PDE-constrained prediction in latent space. Extensive experiments conducted on four v…
UC Berkeley（加州大学伯克利分校）；Sinovation Ventures AI Institute（创新工场人工智能研究院）；Columbia University（哥伦比亚大学）
A dynamic scene has two types of elements: those that move fluidly and can be predicted from previous frames, and those which are disoccluded (exposed) and cannot be extrapolated. Prior approaches to video prediction typically learn either to warp or to hallucinate future pixels, but not both. In this paper, we describe a computational model for high-fidelity video prediction which disentangles motion-specific propagation from motion-agnostic generation. We introduce a confidence-aware warping operator which gates the output of pixel predictions from a flow predictor for non-occluded regions a…
Image editing using a pretrained StyleGAN generator has emerged as a powerful paradigm for facial editing, providing disentangled controls over age, expression, illumination, etc. However, the approach cannot be directly adopted for video manipulations. We hypothesize that the main missing ingredient is the lack of fine-grained and disentangled control over face location, face pose, and local facial expressions. In this work, we demonstrate that such a fine-grained control is indeed achievable using pretrained StyleGAN by working across multiple (latent) spaces (namely, the positional space, t…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
In many vision-based reinforcement learning (RL) problems, the agent controls a movable object in its visual field, e.g., the player's avatar in video games and the robotic arm in visual grasping and manipulation. Leveraging action-conditioned video prediction, we propose an end-to-end learning framework to disentangle the controllable object from the observation signal. The disentangled representation is shown to be useful for RL as additional observation channels to the agent. Experiments on a set of Atari games with the popular Double DQN algorithm demonstrate improved sample efficiency and…
Iskenderun Technical University（伊斯肯德伦技术大学）；Imperial College London（帝国理工学院）；Hacettepe University（哈塞特佩大学）；Koc University（科奇大学）
Giving machines the ability to imagine possible new objects or scenes from linguistic descriptions and produce their realistic renderings is arguably one of the most challenging problems in computer vision. Recent advances in deep generative models have led to new approaches that give promising results towards this goal. In this paper, we introduce a new method called DiCoMoGAN for manipulating videos with natural language, aiming to perform local and semantic edits on a video clip to alter the appearances of an object of interest. Our GAN architecture allows for better utilization of multiple…
In this work we present an adversarial training algorithm that exploits correlations in video to learn --without supervision-- an image generator model with a disentangled latent space. The proposed methodology requires only a few modifications to the standard algorithm of Generative Adversarial Networks (GAN) and involves training with sets of frames taken from short videos. We train our model over two datasets of face-centered videos which present different people speaking or moving the head: VidTIMIT and YouTube Faces datasets. We found that our proposal allows us to split the generator lat…
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…
Inria（法国国家信息与自动化研究所）；Université Côte d’Azur（蔚蓝海岸大学）；University of Warsaw（华沙大学）
Creating realistic human videos entails the challenge of being able to simultaneously generate both appearance, as well as motion. To tackle this challenge, we introduce G$^{3}$AN, a novel spatio-temporal generative model, which seeks to capture the distribution of high dimensional video data and to model appearance and motion in disentangled manner. The latter is achieved by decomposing appearance and motion in a three-stream Generator, where the main stream aims to model spatio-temporal consistency, whereas the two auxiliary streams augment the main stream with multi-scale appearance and mot…
Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）
There are many forms of feature information present in video data. Principle among them are object identity information which is largely static across multiple video frames, and object pose and style information which continuously transforms from frame to frame. Most existing models confound these two types of representation by mapping them to a shared feature space. In this paper we propose a probabilistic approach for learning separable representations of object identity and pose information using unsupervised video data. Our approach leverages a deep generative model with a factored prior d…
Video composition aims to generate a composite video by combining the foreground of one video with the background of another video, but the inserted foreground may be incompatible with the background in terms of color and illumination. Video harmonization aims to adjust the foreground of a composite video to make it compatible with the background. So far, video harmonization has only received limited attention and there is no public dataset for video harmonization. In this work, we construct a new video harmonization dataset HYouTube by adjusting the foreground of real videos to create synthet…
University of Technology Sydney（悉尼科技大学）；Baidu Research（百度研究院）
This paper investigates the principles of embedding learning to tackle the challenging semi-supervised video object segmentation. Different from previous practices that only explore the embedding learning using pixels from foreground object (s), we consider background should be equally treated and thus propose Collaborative video object segmentation by Foreground-Background Integration (CFBI) approach. Our CFBI implicitly imposes the feature embedding from the target foreground object and its corresponding background to be contrastive, promoting the segmentation results accordingly. With the f…
This work presents a new robust PCA method for foreground-background separation on freely moving camera video with possible dense and sparse corruptions. Our proposed method registers the frames of the corrupted video and then encodes the varying perspective arising from camera motion as missing data in a global model. This formulation allows our algorithm to produce a panoramic background component that automatically stitches together corrupted data from partially overlapping frames to reconstruct the full field of view. We model the registered video as the sum of a low-rank component that ca…
Zhejiang University（浙江大学）；University of Electronic Science and Technology of China（电子科技大学）
The data storage has been one of the bottlenecks in surveillance systems. The conventional video compression algorithms such as H.264 and H.265 do not fully utilize the low information density characteristic of the surveillance video. In this paper, we propose a video compression method that extracts and compresses the foreground and background of the video separately. The compression ratio is greatly improved by sharing background information among multiple adjacent frames through an adaptive background updating and interpolation module. Besides, we present two different schemes to compress t…
This paper presents a novel framework in which video/image segmentation and localization are cast into a single optimization problem that integrates information from low level appearance cues with that of high level localization cues in a very weakly supervised manner. The proposed framework leverages two representations at different levels, exploits the spatial relationship between bounding boxes and superpixels as linear constraints and simultaneously discriminates between foreground and background at bounding box and superpixel level. Different from previous approaches that mainly rely on d…
Institute of Computing Technology, CAS（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；University of Oulu（奥卢大学）；Peng Cheng Laboratory（鹏城实验室）
Remote physiological measurements, e.g., remote photoplethysmography (rPPG) based heart rate (HR), heart rate variability (HRV) and respiration frequency (RF) measuring, are playing more and more important roles under the application scenarios where contact measurement is inconvenient or impossible. Since the amplitude of the physiological signals is very small, they can be easily affected by head movements, lighting conditions, and sensor diversities. To address these challenges, we propose a cross-verified feature disentangling strategy to disentangle the physiological features with non-phys…
This paper investigates the principles of embedding learning to tackle the challenging semi-supervised video object segmentation. Unlike previous practices that focus on exploring the embedding learning of foreground object (s), we consider background should be equally treated. Thus, we propose a Collaborative video object segmentation by Foreground-Background Integration (CFBI) approach. CFBI separates the feature embedding into the foreground object region and its corresponding background region, implicitly promoting them to be more contrastive and improving the segmentation results accordin…
This work presents a novel approach for robust PCA with total variation regularization for foreground-background separation and denoising on noisy, moving camera video. Our proposed algorithm registers the raw (possibly corrupted) frames of a video and then jointly processes the registered frames to produce a decomposition of the scene into a low-rank background component that captures the static components of the scene, a smooth foreground component that captures the dynamic components of the scene, and a sparse component that can isolate corruptions and other non-idealities. Unlike existing …
We identify a novel instance of the background subtraction problem that focuses on extracting near-field foreground objects captured using handheld cameras. Given two user-generated videos of a scene, one with and the other without the foreground object(s), our goal is to efficiently generate an output video with only the foreground object(s) present in it. We cast this challenge as a spatio-temporal frame matching problem, and propose an efficient solution for it that exploits the temporal smoothness of the video sequences. We present theoretical analyses for the error bounds of our approach,…
University of British Columbia（不列颠哥伦比亚大学）；Vector Institute for AI（向量人工智能研究所）
We introduce layered controllable video generation, where we, without any supervision, decompose the initial frame of a video into foreground and background layers, with which the user can control the video generation process by simply manipulating the foreground mask. The key challenges are the unsupervised foreground-background separation, which is ambiguous, and ability to anticipate user manipulations with access to only raw video sequences. We address these challenges by proposing a two-stage learning procedure. In the first stage, with the rich set of losses and dynamic foreground size p…
PAI-Studio: Cinematic Video Background Replacement with Camera-Aware Motion
Utopai Studios（Utopai工作室）；Nanyang Technological University（南洋理工大学）；University of California, Irvine（加州大学尔湾分校）；Show Lab, National University of Singapore（新加坡国立大学Show实验室）
Vrije Universiteit Brussel（布鲁塞尔自由大学）；imec（欧洲微电子研究中心）；Weizmann Institute of Science（魏茨曼科学研究所）
Deep unfolded neural networks are designed by unrolling the iterations of optimization algorithms. They can be shown to achieve faster convergence and higher accuracy than their optimization counterparts. This paper proposes a new deep-unfolding-based network design for the problem of Robust Principal Component Analysis (RPCA) with application to video foreground-background separation. Unlike existing designs, our approach focuses on modeling the temporal correlation between the sparse representations of consecutive video frames. To this end, we perform the unfolding of an iterative algorithm …
Detecting moving objects from ground-based videos is commonly achieved by using background subtraction techniques. Low-rank matrix decomposition inspires a set of state-of-the-art approaches for this task. It is integrated with structured sparsity regularization to achieve background subtraction in the developed method of Low-rank and Structured Sparse Decomposition (LSD). However, when this method is applied to satellite videos where spatial resolution is poor and targets' contrast to the background is low, its performance is limited as the data no longer fits adequately either the foreground…
Video harmonization aims to adjust the foreground of a composite video to make it compatible with the background. So far, video harmonization has only received limited attention and there is no public dataset for video harmonization. In this work, we construct a new video harmonization dataset HYouTube by adjusting the foreground of real videos to create synthetic composite videos. Moreover, we consider the temporal consistency in video harmonization task. Unlike previous works which establish the spatial correspondence, we design a novel framework based on the assumption of color mapping cons…
Disentangling spatio-temporal knowledge for weakly supervised object detection and segmentation in surgical video
University of Pennsylvania（宾夕法尼亚大学）；Penn Computer Assisted Surgery and Outcomes Laboratory（宾夕法尼亚计算机辅助外科与结局实验室）；Department of Surgery, University of Pennsylvania（宾夕法尼亚大学外科系）；Department of Electrical and Systems Engineering, University of Pennsylvania（宾夕法尼亚大学电气与系统工程系）；Department of Computer and Information Science, University of Pennsylvania（宾夕法尼亚大学计算机与信息科学系）
Shanghai Jiao Tong University（上海交通大学）；Tencent AI Lab（腾讯人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；University of Michigan（密歇根大学）
In light of the success of contrastive learning in the image domain, current self-supervised video representation learning methods usually employ contrastive loss to facilitate video representation learning. When naively pulling two augmented views of a video closer, the model however tends to learn the common static background as a shortcut but fails to capture the motion information, a phenomenon dubbed as background bias. Such bias makes the model suffer from weak generalization ability, leading to worse performance on downstream tasks such as action recognition. To alleviate such bias, we …
This paper introduces the method of dynamic mode decomposition (DMD) for robustly separating video frames into background (low-rank) and foreground (sparse) components in real-time. The method is a novel application of a technique used for characterizing nonlinear dynamical systems in an equation-free manner by decomposing the state of the system into low-rank terms whose Fourier components in time are known. DMD terms with Fourier frequencies near the origin (zero-modes) are interpreted as background (low-rank) portions of the given video frames, and the terms with Fourier frequencies bounded…
Robust foreground object segmentation via background modelling is a difficult problem in cluttered environments, where obtaining a clear view of the background to model is almost impossible. In this paper, we propose a method capable of robustly estimating the background and detecting regions of interest in such environments. In particular, we propose to extend the background initialisation component of a recent patch-based foreground detection algorithm with an elaborate technique based on Markov Random Fields, where the optimal labelling solution is computed using iterated conditional modes.…
This paper presents static object detection and segmentation method in videos from cluttered scenes. Robust static object detection is still challenging task due to presence of moving objects in many surveillance applications. The level of difficulty is extremely influenced by on how you label the object to be identified as static that do not establish the original background but appeared in the video at different time. In this context, background subtraction technique based on the frame difference concept is applied to the identification of static objects. Firstly, we estimate a frame differe…
Recent works have shown how realistic talking face images can be obtained under the supervision of geometry guidance, e.g., facial landmark or boundary. To alleviate the demand for manual annotations, in this paper, we propose a novel self-supervised hybrid model (DAE-GAN) that learns how to reenact face naturally given large amounts of unlabeled videos. Our approach combines two deforming autoencoders with the latest advances in the conditional generation. On the one hand, we adopt the deforming autoencoder to disentangle identity and pose representations. A strong prior in talking face video…
Beihang University（北京航空航天大学）；Peking University（北京大学）；Alibaba Group（阿里巴巴集团）；SenseTime Group Limited（商汤集团有限公司）
Segmenting primary objects in a video is an important yet challenging problem in computer vision, as it exhibits various levels of foreground/background ambiguities. To reduce such ambiguities, we propose a novel formulation via exploiting foreground and background context as well as their complementary constraint. Under this formulation, a unified objective function is further defined to encode each cue. For implementation, we design a Complementary Segmentation Network (CSNet) with two separate branches, which can simultaneously encode the foreground and background information along with joi…
ByteDance AI Lab（字节跳动人工智能实验室）；Huazhong University of Science and Technology（华中科技大学）
Although deep learning based methods have achieved great progress in unsupervised video object segmentation, difficult scenarios (e.g., visual similarity, occlusions, and appearance changing) are still not well-handled. To alleviate these issues, we propose a novel Focus on Foreground Network (F2Net), which delves into the intra-inter frame details for the foreground objects and thus effectively improve the segmentation performance. Specifically, our proposed network consists of three main parts: Siamese Encoder Module, Center Guiding Appearance Diffusion Module, and Dynamic Information Fusion…
Large intra-class variation is the result of changes in multiple object characteristics. Images, however, only show the superposition of different variable factors such as appearance or shape. Therefore, learning to disentangle and represent these different characteristics poses a great challenge, especially in the unsupervised case. Moreover, large object articulation calls for a flexible part-based model. We present an unsupervised approach for disentangling appearance and shape by learning parts consistently over all instances of a category. Our model for learning an object representation i…
University of Edinburgh（爱丁堡大学）；Google Research（谷歌研究院）
Given unstructured videos of deformable objects, we automatically recover spatiotemporal correspondences to map one object to another (such as animals in the wild). While traditional methods based on appearance fail in such challenging conditions, we exploit consistency in object motion between instances. Our approach discovers pairs of short video intervals where the object moves in a consistent manner and uses these candidates as seeds for spatial alignment. We model the spatial correspondence between the point trajectories on the object in one interval to those in the other using a time-var…
Institute of Mathematics of the Romanian Academy（罗马尼亚科学院数学研究所）
Unsupervised learning from visual data is one of the most difficult challenges in computer vision, being a fundamental task for understanding how visual recognition works. From a practical point of view, learning from unsupervised visual input has an immense practical value, as very large quantities of unlabeled videos can be collected at low cost. In this paper, we address the task of unsupervised learning to detect and segment foreground objects in single images. We achieve our goal by training a student pathway, consisting of a deep neural network. It learns to predict from a single input i…
Zhejiang University（浙江大学）；Zhejiang Gongshang University（浙江工商大学）；National University of Singapore（新加坡国立大学）；Shandong Normal Unversity（山东师范大学）；Nanyang Technological University（南洋理工大学）；University of Science and Technology of China（中国科学技术大学）
One compelling application of artificial intelligence is to generate a video of a target person performing arbitrary desired motion (from a source person). While the state-of-the-art methods are able to synthesize a video demonstrating similar broad stroke motion details, they are generally lacking in texture details. A pertinent manifestation appears as distorted face, feet, and hands, and such flaws are very sensitively perceived by human observers. Furthermore, current methods typically employ GANs with a L2 loss to assess the authenticity of the generated videos, inherently requiring a lar…
Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models
Peking University（北京大学）；Kunbyte AI（昆字科技）；University of Chinese Academy of Sciences（中国科学院大学）；Zhejiang University（浙江大学）；Hangzhou Normal University（杭州师范大学）
Insight Centre for Data Analytics（Insight数据分析中心）；Dublin City University（都柏林城市大学）；Universidad Autónoma de Madrid（马德里自治大学）
This paper presents a novel approach for segmenting moving objects in unconstrained environments using guided convolutional neural networks. This guiding process relies on foreground masks from independent algorithms (i.e. state-of-the-art algorithms) to implement an attention mechanism that incorporates the spatial location of foreground and background to compute their separated representations. Our approach initially extracts two kinds of features for each frame using colour and optical flow information. Such features are combined following a multiplicative scheme to benefit from their compl…
The segmentation of video sequences into foreground and background regions is a low-level process commonly used in video content analysis and smart surveillance applications. Using a multispectral camera setup can improve this process by providing more diverse data to help identify objects despite adverse imaging conditions. The registration of several data sources is however not trivial if the appearance of objects produced by each sensor differs substantially. This problem is further complicated when parallax effects cannot be ignored when using close-range stereo pairs. In this work, we pre…
Discovering Local Binary Pattern Equation for Foreground Object Removal in Videos
ActiveEon（ActiveEon公司）；CNRS（法国国家科学研究中心）；SIGMA Clermont（克莱蒙 SIGMA 工程师学院）；Institut Pascal（帕斯卡研究所）；University of Clermont Auvergne（克莱蒙奥弗涅大学）；University of La Rochelle（拉罗谢尔大学）；University of Beira Interior（贝拉内政大学）
