Feature Flow: In-network Feature Flow Estimation for Video Object Detection
A*STAR, Institute for Infocomm Research（新加坡科技研究局信息通信研究所）；Nanyang Technological University（南洋理工大学）；Hangzhou Innovation Institute of Beihang University（北京航空航天大学杭州创新研究院）
Ruibing Jin, Guosheng Lin, Changyun Wen, Jianliang Wang, Fayao Liu
Optical flow, which expresses pixel displacement, is widely used in many computer vision tasks to provide pixel-level motion information. However, with the remarkable progress of the convolutional neural network, recent state-of-the-art approaches are proposed to solve problems directly on feature-level. Since the displacement of feature vector is not consistent to the pixel displacement, a common approach is to:forward optical flow to a neural network and fine-tune this network on the task dataset. With this method,they expect the fine-tuned network to produce tensors encoding feature-level motion information. In this paper, we rethink this de facto paradigm and analyze its drawbacks in the video object detection task. To mitigate these issues, we propose a novel network (IFF-Net) with an \textbf{I}n-network \textbf{F}eature \textbf{F}low estimation module (IFF module) for video object detection. Without resorting pre-training on any additional dataset, our IFF module is able to directly produce \textbf{feature flow} which indicates the feature displacement. Our IFF module consists of a shallow module, which shares the features with the detection branches. This compact design enables our IFF-Net to accurately detect objects, while maintaining a fast inference speed. Furthermore, we propose a transformation residual loss (TRL) based on \textit{self-supervision}, which further improves the performance of our IFF-Net. Our IFF-Net outperforms existing methods and sets a state-of-the-art performance on ImageNet VID.
The effectiveness of the approaches to predict 3D poses from 2D poses estimated in each frame of a video has been demonstrated for 3D human pose estimation. However, 2D poses without appearance information of persons have much ambiguity with respect to the joint depths. In this paper, we propose to estimate a 3D pose in each frame of a video and refine it considering temporal information. The proposed approach reduces the ambiguity of the joint depths and improves the 3D pose estimation accuracy.
Video segmentation for the human head and shoulders is essential in creating elegant media for videoconferencing and virtual reality applications. The main challenge is to process high-quality background subtraction in a real-time manner and address the segmentation issues under motion blurs, e.g., shaking the head or waving hands during conference video. To overcome the motion blur problem in video segmentation, we propose a novel flow-based encoder-decoder network (FUNet) that combines both traditional Horn-Schunck optical-flow estimation technique and convolutional neural networks to perfor…
Video annotation is expensive and time consuming. Consequently, datasets for multi-person pose estimation and tracking are less diverse and have more sparse annotations compared to large scale image datasets for human pose estimation. This makes it challenging to learn deep learning based models for associating keypoints across frames that are robust to nuisance factors such as motion blur and occlusions for the task of multi-person pose tracking. To address this issue, we propose an approach that relies on keypoint correspondences for associating persons in videos. Instead of training the net…
Depth-aware video panoptic segmentation tackles the inverse projection problem of restoring panoptic 3D point clouds from video sequences, where the 3D points are augmented with semantic classes and temporally consistent instance identifiers. We propose a novel solution with a multi-task network that performs monocular depth estimation and video panoptic segmentation. Since acquiring ground truth labels for both depth and image segmentation has a relatively large cost, we leverage the power of unlabeled video sequences with self-supervised monocular depth estimation and semi-supervised learnin…
Rochester Institute of Technology（罗切斯特理工学院）；Rochester, NY（罗切斯特，纽约州（注意：这是地址信息，严格按要求不应提取，此处原数据可能有误，正确机构应为Rochester Institute of Technology））
We propose UniPose, a unified framework for human pose estimation, based on our "Waterfall" Atrous Spatial Pooling architecture, that achieves state-of-art-results on several pose estimation metrics. Current pose estimation methods utilizing standard CNN architectures heavily rely on statistical postprocessing or predefined anchor poses for joint localization. UniPose incorporates contextual segmentation and joint localization to estimate the human pose in a single stage, with high accuracy, without relying on statistical postprocessing methods. The Waterfall module in UniPose leverages the ef…
Although many approaches for multi-human pose estimation in videos have shown profound results, they require densely annotated data which entails excessive man labor. Furthermore, there exists occlusion and motion blur that inevitably lead to poor estimation performance. To address these problems, we propose a method that leverages an attention mask for occluded joints and encodes temporal dependency between frames using transformers. First, our framework composes different combinations of sparsely annotated frames that denote the track of the overall joint movement. We propose an occlusion at…
Human pose estimation in video relies on local information by either estimating each frame independently or tracking poses across frames. In this paper, we propose a novel method combining local approaches with global context. We introduce a light weighted, unsupervised, key frame proposal network (K-FPN) to select informative frames and a learned dictionary to recover the entire pose sequence from these frames. The K-FPN speeds up the pose estimation and provides robustness to bad frames with occlusion, motion blur, and illumination changes, while the learned dictionary provides global dynami…
National University of Singapore（新加坡国立大学）；YITU Technology（依图科技）
Video-based human pose estimation in crowded scenes is a challenging problem due to occlusion, motion blur, scale variation and viewpoint change, etc. Prior approaches always fail to deal with this problem because of (1) lacking of usage of temporal information; (2) lacking of training data in crowded scenes. In this paper, we focus on improving human pose estimation in videos of crowded scenes from the perspectives of exploiting temporal context and collecting new data. In particular, we first follow the top-down strategy to detect persons and perform single-person pose estimation for each fr…
Tsinghua University（清华大学）；University of California, Merced（加州大学默塞德分校）
This paper proposes an end-to-end trainable network, SegFlow, for simultaneously predicting pixel-wise object segmentation and optical flow in videos. The proposed SegFlow has two branches where useful information of object segmentation and optical flow is propagated bidirectionally in a unified framework. The segmentation branch is based on a fully convolutional network, which has been proved effective in image segmentation task, and the optical flow branch takes advantage of the FlowNet model. The unified framework is trained iteratively offline to learn a generic notion, and fine-tuned onli…
Deep ConvNets have been shown to be effective for the task of human pose estimation from single images. However, several challenging issues arise in the video-based case such as self-occlusion, motion blur, and uncommon poses with few or no examples in training data sets. Temporal information can provide additional cues about the location of body joints and help to alleviate these issues. In this paper, we propose a deep structured model to estimate a sequence of human poses in unconstrained videos. This model can be efficiently trained in an end-to-end manner and is capable of representing ap…
Human Activity Recognition (HAR) using on-body devices identifies specific human actions in unconstrained environments. HAR is challenging due to the inter and intra-variance of human movements; moreover, annotated datasets from on-body devices are scarce. This problem is mainly due to the difficulty of data creation, i.e., recording, expensive annotation, and lack of standard definitions of human activities. Previous works demonstrated that transfer learning is a good strategy for addressing scenarios with scarce data. However, the scarcity of annotated on-body device datasets remains. This p…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research（微软研究院）
Extending state-of-the-art object detectors from image to video is challenging. The accuracy of detection suffers from degenerated object appearances in videos, e.g., motion blur, video defocus, rare poses, etc. Existing work attempts to exploit temporal information on box level, but such methods are not trained end-to-end. We present flow-guided feature aggregation, an accurate and end-to-end learning framework for video object detection. It leverages temporal coherence on feature level instead. It improves the per-frame features by aggregation of nearby features along the motion paths, and t…
ETH Zürich（苏黎世联邦理工学院）；Facebook AI Research（脸书人工智能研究院）；Google Brain（谷歌大脑）
In this work, we demonstrate that 3D poses in video can be effectively estimated with a fully convolutional model based on dilated temporal convolutions over 2D keypoints. We also introduce back-projection, a simple and effective semi-supervised training method that leverages unlabeled video data. We start with predicted 2D keypoints for unlabeled video, then estimate 3D poses and finally back-project to the input 2D keypoints. In the supervised setting, our fully-convolutional model outperforms the previous best result from the literature by 6 mm mean per-joint position error on Human3.6M, co…
Previous video-based human pose estimation methods have shown promising results by leveraging aggregated features of consecutive frames. However, most approaches compromise accuracy to mitigate jitter or do not sufficiently comprehend the temporal aspects of human motion. Furthermore, occlusion increases uncertainty between consecutive frames, which results in unsmooth results. To address these issues, we design an architecture that exploits the keypoint kinematic features with the following components. First, we effectively capture the temporal features by leveraging individual keypoint's vel…
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of California, Irvine（加利福尼亚大学尔湾分校）；Shanghai AI Laboratory（上海人工智能实验室）
Graph Convolution Network (GCN) has been successfully used for 3D human pose estimation in videos. However, it is often built on the fixed human-joint affinity, according to human skeleton. This may reduce adaptation capacity of GCN to tackle complex spatio-temporal pose variations in videos. To alleviate this problem, we propose a novel Dynamical Graph Network (DG-Net), which can dynamically identify human-joint affinity, and estimate 3D pose by adaptively learning spatial/temporal joint relations from videos. Different from traditional graph convolution, we introduce Dynamical Spatial/Tempor…
University of Science and Technology Beijing（北京科技大学）；Baidu Inc.（百度公司）
Video 3D human pose estimation aims to localize the 3D coordinates of human joints from videos. Recent transformer-based approaches focus on capturing the spatiotemporal information from sequential 2D poses, which cannot model the contextual depth feature effectively since the visual depth features are lost in the step of 2D pose estimation. In this paper, we simplify the paradigm into an end-to-end framework, Instance-guided Video Transformer (IVT), which enables learning spatiotemporal contextual depth information from visual features effectively and predicts 3D poses directly from video fra…
Video processing solutions for motion analysis are key tasks in many computer vision applications, ranging from human activity recognition to object detection. In particular, speed estimation algorithms may be relevant in contexts such as street monitoring and environment surveillance. In most realistic scenarios, the projection of a framed object of interest onto the image plane is likely to be affected by dynamic changes mainly related to perspectival transformations or periodic behaviours. Therefore, advanced speed estimation techniques need to rely on robust algorithms for object detection…
Renmin University of China（中国人民大学）；The University of Hong Kong（香港大学）；The Chinese University of Hong Kong（香港中文大学）；SenseTime Research（商汤科技研究院）
A major challenge for video semantic segmentation is the lack of labeled data. In most benchmark datasets, only one frame of a video clip is annotated, which makes most supervised methods fail to utilize information from the rest of the frames. To exploit the spatio-temporal information in videos, many previous works use pre-computed optical flows, which encode the temporal consistency to improve the video segmentation. However, the video segmentation and optical flow estimation are still considered as two separate tasks. In this paper, we propose a novel framework for joint video semantic seg…
Guangdong University of Technology（广东工业大学）；Chinese University of Hong Kong（香港中文大学）
Spatio-temporal information is key to resolve occlusion and depth ambiguity in 3D pose estimation. Previous methods have focused on either temporal contexts or local-to-global architectures that embed fixed-length spatio-temporal information. To date, there have not been effective proposals to simultaneously and flexibly capture varying spatio-temporal sequences and effectively achieves real-time 3D pose estimation. In this work, we improve the learning of kinematic constraints in the human skeleton: posture, local kinematic connections, and symmetry by modeling local and global spatial inform…
Google Research（谷歌研究院）；Massachusetts Institute of Technology（麻省理工学院）；Harvard University（哈佛大学）
Many video enhancement algorithms rely on optical flow to register frames in a video sequence. Precise flow estimation is however intractable; and optical flow itself is often a sub-optimal representation for particular video processing tasks. In this paper, we propose task-oriented flow (TOFlow), a motion representation learned in a self-supervised, task-specific manner. We design a neural network with a trainable motion estimation component and a video processing component, and train them jointly to learn the task-oriented flow. For evaluation, we build Vimeo-90K, a large-scale, high-quality…
The Chinese University of Hong Kong（香港中文大学）；Nanyang Technological University（南洋理工大学）
Video inpainting, which aims at filling in missing regions of a video, remains challenging due to the difficulty of preserving the precise spatial and temporal coherence of video contents. In this work we propose a novel flow-guided video inpainting approach. Rather than filling in the RGB pixels of each frame directly, we consider video inpainting as a pixel propagation problem. We first synthesize a spatially and temporally coherent optical flow field across video frames using a newly designed Deep Flow Completion network. Then the synthesized flow field is used to guide the propagation of p…
Illinois Tech（伊利诺伊理工学院）；Texas State University（德克萨斯州立大学）；Tesla Inc（特斯拉公司）；Cisco Research（思科研究院）
Optical flow estimation has been a long-lasting and fundamental problem in the computer vision community. However, despite the advances of optical flow estimation in perspective videos, the 360$^\circ$ videos counterpart remains in its infancy, primarily due to the shortage of benchmark datasets and the failure to accommodate the omnidirectional nature of 360$^\circ$ videos. We propose the first perceptually realistic 360$^\circ$ filed-of-view video benchmark dataset, namely FLOW360, with 40 different videos and 4,000 video frames. We then conduct comprehensive characteristic analysis and exte…
Video-based physiological signal estimation has been limited primarily to predicting episodic scores in windowed intervals. While these intermittent values are useful, they provide an incomplete picture of patients' physiological status and may lead to late detection of critical conditions. We propose a video Transformer for estimating instantaneous heart rate and respiration rate from face videos. Physiological signals are typically confounded by alignment errors in space and time. To overcome this, we formulated the loss in the frequency domain. We evaluated the method on the large scale Vis…
The problem of video inter-frame interpolation is an essential task in the field of image processing. Correctly increasing the number of frames in the recording while maintaining smooth movement allows to improve the quality of played video sequence, enables more effective compression and creating a slow-motion recording. This paper proposes the FastRIFE algorithm, which is some speed improvement of the RIFE (Real-Time Intermediate Flow Estimation) model. The novel method was examined and compared with other recently published algorithms. All source codes are available at https://gitlab.com/ma…
The dense depth estimation of a 3D scene has numerous applications, mainly in robotics and surveillance. LiDAR and radar sensors are the hardware solution for real-time depth estimation, but these sensors produce sparse depth maps and are sometimes unreliable. In recent years research aimed at tackling depth estimation using single 2D image has received a lot of attention. The deep learning based self-supervised depth estimation methods from the rectified stereo and monocular video frames have shown promising results. We propose a self-attention based depth and ego-motion network for unrectifi…
Dense depth and pose estimation is a vital prerequisite for various video applications. Traditional solutions suffer from the robustness of sparse feature tracking and insufficient camera baselines in videos. Therefore, recent methods utilize learning-based optical flow and depth prior to estimate dense depth. However, previous works require heavy computation time or yield sub-optimal depth results. We present GCVD, a globally consistent method for learning-based video structure from motion (SfM) in this paper. GCVD integrates a compact pose graph into the CNN-based optimization to achieve glo…
For the success of video deblurring, it is essential to utilize information from neighboring frames. Most state-of-the-art video deblurring methods adopt motion compensation between video frames to aggregate information from multiple frames that can help deblur a target frame. However, the motion compensation methods adopted by previous deblurring methods are not blur-invariant, and consequently, their accuracy is limited for blurry frames with different blur amounts. To alleviate this problem, we propose two novel approaches to deblur videos by effectively aggregating information from multipl…
We present a generative method to estimate 3D human motion and body shape from monocular video. Under the assumption that starting from an initial pose optical flow constrains subsequent human motion, we exploit flow to find temporally coherent human poses of a motion sequence. We estimate human motion by minimizing the difference between computed flow fields and the output of an artificial flow renderer. A single initialization step is required to estimate motion over multiple frames. Several regularization functions enhance robustness over time. Our test scenarios demonstrate that optical fl…
Video representation is a key challenge in many computer vision applications such as video classification, video captioning, and video surveillance. In this paper, we propose a novel approach for video representation that captures meaningful information including motion and appearance from a sequence of video frames and compacts it into a single image. To this end, we compute the optical flow and use it in a least squares optimization to find a new image, the so-called Flow Profile Image (FPI). This image encodes motions as well as foreground appearance information while background information…
Video interpolation increases the temporal resolution of a video sequence by synthesizing intermediate frames between two consecutive frames. We propose a novel deep-learning-based video interpolation algorithm based on bilateral motion estimation. First, we develop the bilateral motion network with the bilateral cost volume to estimate bilateral motions accurately. Then, we approximate bi-directional motions to predict a different kind of bilateral motions. We then warp the two input frames using the estimated bilateral motions. Next, we develop the dynamic filter generation network to yield …
Learning to represent and generate videos from unlabeled data is a very challenging problem. To generate realistic videos, it is important not only to ensure that the appearance of each frame is real, but also to ensure the plausibility of a video motion and consistency of a video appearance in the time direction. The process of video generation should be divided according to these intrinsic difficulties. In this study, we focus on the motion and appearance information as two important orthogonal components of a video, and propose Flow-and-Texture-Generative Adversarial Networks (FTGAN) consis…
Future frame prediction in videos is a promising avenue for unsupervised video representation learning. Video frames are naturally generated by the inherent pixel flows from preceding frames based on the appearance and motion dynamics in the video. However, existing methods focus on directly hallucinating pixel values, resulting in blurry predictions. In this paper, we develop a dual motion Generative Adversarial Net (GAN) architecture, which learns to explicitly enforce future-frame predictions to be consistent with the pixel-wise flows in the video through a dual-learning mechanism. The prim…
Appearance and motion are two key components to depict and characterize the video content. Currently, the two-stream models have achieved state-of-the-art performances on video classification. However, extracting motion information, specifically in the form of optical flow features, is extremely computationally expensive, especially for large-scale video classification. In this paper, we propose a motion hallucination network, namely MoNet, to imagine the optical flow features from the appearance features, with no reliance on the optical flow computation. Specifically, MoNet models the tempora…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research（微软研究院）；Microsoft Research Asia（微软亚洲研究院）
Deep convolutional neutral networks have achieved great success on image recognition tasks. Yet, it is non-trivial to transfer the state-of-the-art image recognition networks to videos as per-frame evaluation is too slow and unaffordable. We present deep feature flow, a fast and accurate framework for video recognition. It runs the expensive convolutional sub-network only on sparse key frames and propagates their deep feature maps to other frames via a flow field. It achieves significant speedup as flow computation is relatively fast. The end-to-end training of the whole architecture significa…
We present a new flow-based video completion algorithm. Previous flow completion methods are often unable to retain the sharpness of motion boundaries. Our method first extracts and completes motion edges, and then uses them to guide piecewise-smooth flow completion with sharp edges. Existing methods propagate colors among local flow connections between adjacent frames. However, not all missing regions in a video can be reached in this way because the motion boundaries form impenetrable barriers. Our method alleviates this problem by introducing non-local flow connections to temporally distant…
Northwestern Polytechnical University（西北工业大学）；University of Adelaide（阿德莱德大学）；Noah’s Ark Lab, Huawei（华为诺亚方舟实验室）
Accuracy of depth estimation from static images has been significantly improved recently, by exploiting hierarchical features from deep convolutional neural networks (CNNs). Compared with static images, vast information exists among video frames and can be exploited to improve the depth estimation performance. In this work, we focus on exploring temporal information from monocular videos for depth estimation. Specifically, we take the advantage of convolutional long short-term memory (CLSTM) and propose a novel spatial-temporal CSLTM (ST-CLSTM) structure. Our ST-CLSTM structure can capture not…
PhysFlow: Physics-Aware Optical Flow for Motion Controllable Video Generation
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Zhongguancun Academy（中关村 Academy）；School of Information Science and Technology, University of Science and Technology of China（中国科学技术大学信息科学技术学院）；Beihang University（北京航空航天大学）
Huazhong University of Science and Technology（华中科技大学）；Adobe Research（奥多比研究院）
Temporal consistency is the key challenge of video depth estimation. Previous works are based on additional optical flow or camera poses, which is time-consuming. By contrast, we derive consistency with less information. Since videos inherently exist with heavy temporal redundancy, a missing frame could be recovered from neighboring ones. Inspired by this, we propose the frame masking network (FMNet), a spatial-temporal transformer network predicting the depth of masked frames based on their neighboring frames. By reconstructing masked temporal features, the FMNet can learn intrinsic inter-fra…
In this paper we introduce a novel Depth-Aware Video Saliency approach to predict human focus of attention when viewing RGBD videos on regular 2D screens. We train a generative convolutional neural network which predicts a saliency map for a frame, given the fixation map of the previous frame. Saliency estimation in this scenario is highly important since in the near future 3D video content will be easily acquired and yet hard to display. This can be explained, on the one hand, by the dramatic improvement of 3D-capable acquisition equipment. On the other hand, despite the considerable progress…
Northwestern Polytechnical University（西北工业大学）；Australian National University（澳大利亚国立大学）；Data61, CSIRO（澳大利亚联邦科学与工业研究组织Data61）
Videos for outdoor scene often show unpleasant blur effects due to the large relative motion between the camera and the dynamic objects and large depth variations. Existing works typically focus monocular video deblurring. In this paper, we propose a novel approach to deblurring from stereo videos. In particular, we exploit the piece-wise planar assumption about the scene and leverage the scene flow information to deblur the image. Unlike the existing approach [31] which used a pre-computed scene flow, we propose a single framework to jointly estimate the scene flow and deblur the image, where…
Department of Computer Science, Texas State University, USA（德克萨斯州立大学计算机科学系，美国（注：原机构名中Department of Computer Science属于系级别，按要求提取到大学级别，即Texas State University，美国德克萨斯州立大学））
Nowadays 360 video analysis has become a significant research topic in the field since the appearance of high-quality and low-cost 360 wearable devices. In this paper, we propose a novel LiteFlowNet360 architecture for 360 videos optical flow estimation. We design LiteFlowNet360 as a domain adaptation framework from perspective video domain to 360 video domain. We adapt it from simple kernel transformation techniques inspired by Kernel Transformer Network (KTN) to cope with inherent distortion in 360 videos caused by the sphere-to-plane projection. First, we apply an incremental transformation…
Dog owners are typically capable of recognizing behavioral cues that reveal subjective states of their dogs, such as pain. But automatic recognition of the pain state is very challenging. This paper proposes a novel video-based, two-stream deep neural network approach for this problem. We extract and preprocess body keypoints, and compute features from both keypoints and the RGB representation over the video. We propose an approach to deal with self-occlusions and missing keypoints. We also present a unique video-based dog behavior dataset, collected by veterinary professionals, and annotated …
Texas State University（德克萨斯州立大学）；Illinois Institute of Technology（伊利诺伊理工学院）；Cisco Research（思科研究院）
Optical flow estimation in omnidirectional videos faces two significant issues: the lack of benchmark datasets and the challenge of adapting perspective video-based methods to accommodate the omnidirectional nature. This paper proposes the first perceptually natural-synthetic omnidirectional benchmark dataset with a 360-degree field of view, FLOW360, with 40 different videos and 4,000 video frames. We conduct comprehensive characteristic analysis and comparisons between our dataset and existing optical flow datasets, which manifest perceptual realism, uniqueness, and diversity. To accommodate …
Edge-aware Consistent Stereo Video Depth Estimation
K|Lens GmbH（K|Lens有限公司）；Saarland Informatics Campus（萨尔兰信息学园区）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））；MPI Informatics（马克斯·普朗克信息学研究所）
University of Central Florida（中佛罗里达大学）；Megvii Technology（旷视科技）
In this paper, we present a new inpainting framework for recovering missing regions of video frames. Compared with image inpainting, performing this task on video presents new challenges such as how to preserving temporal consistency and spatial details, as well as how to handle arbitrary input video size and length fast and efficiently. Towards this end, we propose a novel deep learning architecture which incorporates ConvLSTM and optical flow for modeling the spatial-temporal consistency in videos. It also saves much computational resource such that our method can handle videos with larger f…
We propose an optical flow-guided approach for semi-supervised video object segmentation. Optical flow is usually exploited as additional guidance information in unsupervised video object segmentation. However, its relevance in semi-supervised video object segmentation has not been fully explored. In this work, we follow an encoder-decoder approach to address the segmentation task. A model to extract the combined information from optical flow and the image is proposed, which is then used as input to the target model and the decoder network. Unlike previous methods where concatenation is used t…
