Recent approaches for fast semantic video segmentation have reduced redundancy by warping feature maps across adjacent frames, greatly speeding up the inference phase. However, the accuracy drops seriously owing to the errors incurred by warping. In this paper, we propose a novel framework and design a simple and effective correction stage after warping. Specifically, we build a non-key-frame CNN, fusing warped context features with current spatial details. Based on the feature fusion, our Context Feature Rectification~(CFR) module learns the model's difference from a per-frame model to correct the warped features. Furthermore, our Residual-Guided Attention~(RGA) module utilizes the residual maps in the compressed domain to help CRF focus on error-prone regions. Results on Cityscapes show that the accuracy significantly increases from $67.3\%$ to $71.6\%$, and the speed edges down from $65.5$ FPS to $61.8$ FPS at a resolution of $1024\times 2048$. For non-rigid categories, e.g., ``human'' and ``object'', the improvements are even higher than 18 percentage points.
We consider the task of semi-supervised video object segmentation (VOS). Our approach mitigates shortcomings in previous VOS work by addressing detail preservation and temporal consistency using visual warping. In contrast to prior work that uses full optical flow, we introduce a new foreground-targeted visual warping approach that learns flow fields from VOS data. We train a flow module to capture detailed motion between frames using two weakly-supervised losses. Our object-focused approach of warping previous foreground object masks to their positions in the target frame enables detailed mas…
We address weakly supervised action alignment and segmentation in videos, where only the order of occurring actions is available during training. We propose Discriminative Differentiable Dynamic Time Warping (D3TW), the first discriminative model using weak ordering supervision. The key technical challenge for discriminative modeling with weak supervision is that the loss function of the ordering supervision is usually formulated using dynamic programming and is thus not differentiable. We address this challenge with a continuous relaxation of the min-operator in dynamic programming and extend…
Besides per-pixel accuracy, topological correctness is also crucial for the segmentation of images with fine-scale structures, e.g., satellite images and biomedical images. In this paper, by leveraging the theory of digital topology, we identify pixels in an image that are critical for topology. By focusing on these critical pixels, we propose a new homotopy warping loss to train deep image segmentation networks for better topological accuracy. To efficiently identify these topologically critical pixels, we propose a new algorithm exploiting the distance transform. The proposed algorithm, as w…
Parallax-tolerant Image Stitching via Segmentation-guided Multi-homography Warping
College of Information Science and Engineering, Henan University of Technology（河南工业大学信息科学与工程学院）；Hong Kong University of Science and Technology（香港科技大学）；School of Mathematical Sciences, Shenzhen University（深圳大学数学科学学院）
A common challenge posed to robust semantic segmentation is the expensive data annotation cost. Existing semi-supervised solutions show great potential for solving this problem. Their key idea is constructing consistency regularization with unsupervised data augmentation from unlabeled data for model training. The perturbations for unlabeled data enable the consistency training loss, which benefits semi-supervised semantic segmentation. However, these perturbations destroy image context and introduce unnatural boundaries, which is harmful for semantic segmentation. Besides, the widely adopted …
MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）；Bernstein Center for Computational Neuroscience（伯恩斯坦计算神经科学中心）；NVIDIA（英伟达）；University of Würzburg（维尔茨堡大学）
In this work, we propose a technique to convert CNN models for semantic segmentation of static images into CNNs for video data. We describe a warping method that can be used to augment existing architectures with very little extra computational cost. This module is called NetWarp and we demonstrate its use for a range of network architectures. The main design principle is to use optical flow of adjacent frames for warping internal network representations across time. A key insight of this work is that fast optical flow methods can be combined with many different CNN architectures for improved …
Imperial College London（帝国理工学院）；Coventry University（考文垂大学）；St Mary’s Hospital（圣玛丽医院）；Shanghai JiaoTong University（上海交通大学）
Accurate real-time catheter segmentation is an important pre-requisite for robot-assisted endovascular intervention. Most of the existing learning-based methods for catheter segmentation and tracking are only trained on small-scale datasets or synthetic data due to the difficulties of ground-truth annotation. Furthermore, the temporal continuity in intraoperative imaging sequences is not fully utilised. In this paper, we present FW-Net, an end-to-end and real-time deep learning framework for endovascular intervention. The proposed FW-Net has three modules: a segmentation network with encoder-d…
University of Illinois at Urbana-Champaign (UIUC)（伊利诺伊大学厄巴纳-香槟分校）；Pohang University of Science and Technology (POSTECH)（浦项科技大学）
Most recent studies on detecting and localizing temporal anomalies have mainly employed deep neural networks to learn the normal patterns of temporal data in an unsupervised manner. Unlike them, the goal of our work is to fully utilize instance-level (or weak) anomaly labels, which only indicate whether any anomalous events occurred or not in each instance of temporal data. In this paper, we present WETAS, a novel framework that effectively identifies anomalous temporal segments (i.e., consecutive time points) in an input instance. WETAS learns discriminative features from the instance-level l…
We propose an efficient plug-and-play acceleration framework for semi-supervised video object segmentation by exploiting the temporal redundancies in videos presented by the compressed bitstream. Specifically, we propose a motion vector-based warping method for propagating segmentation masks from keyframes to other frames in a bi-directional and multi-hop manner. Additionally, we introduce a residual-based correction module that can fix wrongly propagated segmentation masks from noisy or erroneous motion vectors. Our approach is flexible and can be added on top of several existing video object…
Soongsil University（崇实大学）；Korea Advanced Institute of Science and Technology（韩国科学技术院）；Nestyle Inc.（Nestyle公司）
Image-based virtual try-on aims to synthesize an image of a person wearing a given clothing item. To solve the task, the existing methods warp the clothing item to fit the person's body and generate the segmentation map of the person wearing the item before fusing the item with the person. However, when the warping and the segmentation generation stages operate individually without information exchange, the misalignment between the warped clothes and the segmentation map occurs, which leads to the artifacts in the final image. The information disconnection also causes excessive warping near th…
In this paper, we propose a fast fully convolutional neural network (FCNN) for crowd segmentation. By replacing the fully connected layers in CNN with 1 by 1 convolution kernels, FCNN takes whole images as inputs and directly outputs segmentation maps by one pass of forward propagation. It has the property of translation invariance like patch-by-patch scanning but with much lower computation cost. Once FCNN is learned, it can process input images of any sizes without warping them to a standard size. These attractive properties make it extendable to other general image segmentation problems. Ba…
Athinoula A. Martinos Center for Biomedical Imaging（阿西努拉·A·马蒂诺斯生物医学成像中心）；Massachusetts Institute of Technology（麻省理工学院）
In recent years, learning-based image registration methods have gradually moved away from direct supervision with target warps to instead use self-supervision, with excellent results in several registration benchmarks. These approaches utilize a loss function that penalizes the intensity differences between the fixed and moving images, along with a suitable regularizer on the deformation. In this paper, we argue that the relative failure of supervised registration approaches can in part be blamed on the use of regular U-Nets, which are jointly tasked with feature extraction, feature matching, …
Urban facade segmentation from automatically acquired imagery, in contrast to traditional image segmentation, poses several unique challenges. 360-degree photospheres captured from vehicles are an effective way to capture a large number of images, but this data presents difficult-to-model warping and stitching artifacts. In addition, each pixel can belong to multiple facade elements, and different facade elements (e.g., window, balcony, sill, etc.) are correlated and vary wildly in their characteristics. In this paper, we propose three network architectures of varying complexity to achieve mul…
National Yang Ming Chiao Tung University（台湾阳明交通大学）
This paper addresses fast semantic segmentation on video.Video segmentation often calls for real-time, or even fasterthan real-time, processing. One common recipe for conserving computation arising from feature extraction is to propagate features of few selected keyframes. However, recent advances in fast image segmentation make these solutions less attractive. To leverage fast image segmentation for furthering video segmentation, we propose a simple yet efficient propagation framework. Specifically, we perform lightweight flow estimation in 1/8-downscaled image space for temporal warping in s…
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Huawei Noahs Ark Lab（华为诺亚方舟实验室）
Real-time semantic video segmentation is a challenging task due to the strict requirements of inference speed. Recent approaches mainly devote great efforts to reducing the model size for high efficiency. In this paper, we rethink this problem from a different viewpoint: using knowledge contained in compressed videos. We propose a simple and effective framework, dubbed TapLab, to tap into resources from the compressed domain. Specifically, we design a fast feature warping module using motion vectors for acceleration. To reduce the noise introduced by motion vectors, we design a residual-guided…
When a deep neural network is trained on data with only image-level labeling, the regions activated in each image tend to identify only a small region of the target object. We propose a method of using videos automatically harvested from the web to identify a larger region of the target object by using temporal information, which is not present in the static image. The temporal variations in a video allow different regions of the target object to be activated. We obtain an activated region in each frame of a video, and then aggregate the regions from successive frames into a single image, usin…
Convolutional networks optimized for accuracy on challenging, dense prediction tasks are prohibitively slow to run on each frame in a video. The spatial similarity of nearby video frames, however, suggests opportunity to reuse computation. Existing work has explored basic feature reuse and feature warping based on optical flow, but has encountered limits to the speedup attainable with these techniques. In this paper, we present a new, two part approach to accelerating inference on video. First, we propose a fast feature propagation technique that utilizes the block motion vectors present in co…
The Chinese University of Hong Kong（香港中文大学）；Harbin Institute of Technology（哈尔滨工业大学）；SenseTime Group Limited（商汤集团有限公司）
Conventional video segmentation methods often rely on temporal continuity to propagate masks. Such an assumption suffers from issues like drifting and inability to handle large displacement. To overcome these issues, we formulate an effective mechanism to prevent the target from being lost via adaptive object re-identification. Specifically, our Video Object Segmentation with Re-identification (VS-ReID) model includes a mask propagation module and a ReID module. The former module produces an initial probability map by flow warping while the latter module retrieves missing instances by adaptive…
National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别国家重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Key Laboratory of Machine Perception (MOE), Peking University（北京大学机器感知与智能教育部重点实验室）；SenseTime Research（商汤科技研究院）
This paper proposes a novel method for high-quality image segmentation of both objects and scenes. Inspired by the dilation and erosion operations in morphological image processing techniques, the pixel-level image segmentation problems are treated as squeezing object boundaries. From this perspective, a novel and efficient \textbf{Boundary Squeeze} module is proposed. This module is used to squeeze the object boundary from both inner and outer directions, which contributes to precise mask representation. A bi-directionally flow-based warping process is proposed to generate such squeezed featu…
Closer to Ground Truth: Realistic Shape and Appearance Labeled Data Generation for Unsupervised Underwater Image Segmentation
NORCE Norwegian Research Center AS（NORCE挪威研究中心）；National University of Science and Technology "Politehnica" Bucharest（布加勒斯特理工科学技术大学）；"Simion Stoilow" Institute of Mathematics of the Romanian Academy（罗马尼亚科学院西米翁斯托伊洛夫数学研究所）
We propose a new deep learning approach for automatic detection and segmentation of fluid within retinal OCT images. The proposed framework utilizes both ResNet and Encoder-Decoder neural network architectures. When training the network, we apply a novel data augmentation method called myopic warping together with standard rotation-based augmentation to increase the training set size to 45 times the original amount. Finally, the network output is post-processed with an energy minimization algorithm (graph cut) along with a few other knowledge guided morphological operations to finalize the seg…
Models optimized for accuracy on single images are often prohibitively slow to run on each frame in a video. Recent work exploits the use of optical flow to warp image features forward from select keyframes, as a means to conserve computation on video. This approach, however, achieves only limited speedup, even when optimized, due to the accuracy degradation introduced by repeated forward warping, and the inference cost of optical flow estimation. To address these problems, we propose a new scheme that propagates features using the block motion vectors (BMV) present in compressed video (e.g. H…
Facebook AI Research（Facebook 人工智能研究院）；Inria Grenoble, Laboratoire Jean Kuntzmann, Université Grenoble Alpes（格勒诺布尔阿尔卑斯大学 Jean Kuntzmann 实验室、法国国家信息与自动化研究所格勒诺布尔中心）；New York University（纽约大学）
The ability to predict and therefore to anticipate the future is an important attribute of intelligence. It is also of utmost importance in real-time systems, e.g. in robotics or autonomous driving, which depend on visual scene understanding for decision making. While prediction of the raw RGB pixel values in future video frames has been studied in previous work, here we introduce the novel task of predicting semantic segmentations of future frames. Given a sequence of video frames, our goal is to predict segmentation maps of not yet observed video frames that lie up to a second or further in …
We present Accel, a novel semantic video segmentation system that achieves high accuracy at low inference cost by combining the predictions of two network branches: (1) a reference branch that extracts high-detail features on a reference keyframe, and warps these features forward using frame-to-frame optical flow estimates, and (2) an update branch that computes features of adjustable quality on the current frame, performing a temporal update at each video frame. The modularity of the update branch, where feature subnetworks of varying layer depth can be inserted (e.g. ResNet-18 to ResNet-101)…
Uncertainty-Aware Concept and Motion Segmentation for Semi-Supervised Angiography Videos
School of Mathematical Sciences, Ocean University of China, China（中国海洋大学数学科学学院）；School of Haide, Ocean University of China, China（中国海洋大学海德学院）；School of Computer Science and Engineering, Central South University, China（中南大学计算机科学与工程学院）；The Second Xiangya Hospital of Central South University, China（中南大学湘雅医院第二医院）；School of Intelligent Science and Technology, Nanjing University, China（南京大学智能科学与技术学院）
National University of Singapore（新加坡国立大学）；Shandong AI Institute（山东人工智能研究院）
Accuracy and processing speed are two important factors that affect the use of video object segmentation (VOS) in real applications. With the advanced techniques of deep neural networks, the accuracy has been significantly improved, however, the speed is still far below the real-time needs because of the complicated network design, such as the requirement of the first frame fine-tuning step. To overcome this limitation, we propose a novel mask transfer network (MTN), which can greatly boost the processing speed of VOS and also achieve a reasonable accuracy. The basic idea of MTN is to transfer…
StyleSeg V2: Towards Robust One-shot Segmentation of Brain Tissue via Optimization-free Registration Error Perception
Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology（华中科技大学武汉光电国家研究中心）；Wuhan United Imaging Healthcare Surgical Technology Co., Ltd.（武汉联影外科技术有限公司）
The purpose of this paper is to describe one-shot-learning gesture recognition systems developed on the \textit{ChaLearn Gesture Dataset}. We use RGB and depth images and combine appearance (Histograms of Oriented Gradients) and motion descriptors (Histogram of Optical Flow) for parallel temporal segmentation and recognition. The Quadratic-Chi distance family is used to measure differences between histograms to capture cross-bin relationships. We also propose a new algorithm for trimming videos --- to remove all the unimportant frames from videos. We present two methods that use combination of…
Video object removal is a challenging task in video processing that often requires massive human efforts. Given the mask of the foreground object in each frame, the goal is to complete (inpaint) the object region and generate a video without the target object. While recently deep learning based methods have achieved great success on the image inpainting task, they often lead to inconsistent results between frames when applied to videos. In this work, we propose a novel learning-based Video Object Removal Network (VORNet) to solve the video object removal task in a spatio-temporally consistent …
We present recurrent geometry-aware neural networks that integrate visual information across multiple views of a scene into 3D latent feature tensors, while maintaining an one-to-one mapping between 3D physical locations in the world scene and latent feature locations. Object detection, object segmentation, and 3D reconstruction is then carried out directly using the constructed 3D feature memory, as opposed to any of the input 2D images. The proposed models are equipped with differentiable egomotion-aware feature warping and (learned) depth-aware unprojection operations to achieve geometrical…
Match4Annotate: Cross-Video Annotation Transfer in Ultrasound via Implicit Feature Flow-Guided Matching
Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, USA（麻省理工学院机械工程系）；Institute for Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge, USA（麻省理工学院医学工程与科学研究所）；MIT.nano Immersion Lab, Massachusetts Institute of Technology, Cambridge, USA（麻省理工学院MIT.nano沉浸实验室）
The best performance in Air-tissue boundary (ATB) segmentation of real-time Magnetic Resonance Imaging (rtMRI) videos in speech production is known to be achieved by a 3-dimensional convolutional neural network (3D-CNN) model. However, the evaluation of this model, as well as other ATB segmentation techniques reported in the literature, is done using Dynamic Time Warping (DTW) distance between the entire original and predicted contours. Such an evaluation measure may not capture local errors in the predicted contour. Careful analysis of predicted contours reveals errors in regions like the vel…
Distilling Temporal Coherence into 2D Networks for Transrectal Ultrasound Prostate Video Segmentation
Interdisciplinary Program in Bioengineering, Seoul National University（首尔大学生物工程跨学科项目）；Department of Transdisciplinary Medicine, Seoul National University Hospital（首尔大学医院跨学科医学系）；Department of Artificial Intelligence, Yonsei University（延世大学人工智能系）；Department of Radiology, Seoul National University Hospital（首尔大学医院放射科）
University of Toronto（多伦多大学）；Huawei Technologies（华为技术有限公司）
Video frame interpolation~(VFI) algorithms have improved considerably in recent years due to unprecedented progress in both data-driven algorithms and their implementations. Recent research has introduced advanced motion estimation or novel warping methods as the means to address challenging VFI scenarios. However, none of the published VFI works considers the spatially non-uniform characteristics of the interpolation error (IE). This work introduces such a solution. By closely examining the correlation between optical flow and IE, the paper proposes novel error prediction metrics that partiti…
We introduce multigrid Predictive Filter Flow (mgPFF), a framework for unsupervised learning on videos. The mgPFF takes as input a pair of frames and outputs per-pixel filters to warp one frame to the other. Compared to optical flow used for warping frames, mgPFF is more powerful in modeling sub-pixel movement and dealing with corruption (e.g., motion blur). We develop a multigrid coarse-to-fine modeling strategy that avoids the requirement of learning large filters to capture large displacement. This allows us to train an extremely compact model (4.6MB) which operates in a progressive way ove…
Qualcomm AI Research（高通人工智能研究院）；University of Amsterdam（阿姆斯特丹大学）
This paper aims to accelerate video stream processing, such as object detection and semantic segmentation, by leveraging the temporal redundancies that exist between video frames. Instead of propagating and warping features using motion alignment, such as optical flow, we propose a novel knowledge distillation schema coined as Delta Distillation. In our proposal, the student learns the variations in the teacher's intermediate features over time. We demonstrate that these temporal variations can be effectively distilled due to the temporal redundancies within video frames. During inference, bot…
DeGenseGS: Geometrically and Semantically Decoupled Surgical Scene Understanding in 4D Gaussian Splatting
School of Automation, Southeast University（东南大学自动化学院）；School of Internet of Things, Nanjing University of Posts and Telecommunications（南京邮电大学物联网学院）；Department of Biomedical Engineering, National University of Singapore（新加坡国立大学生物医学工程系）
Semantic understanding and localization are fundamental enablers of robot autonomy that have for the most part been tackled as disjoint problems. While deep learning has enabled recent breakthroughs across a wide spectrum of scene understanding tasks, its applicability to state estimation tasks has been limited due to the direct formulation that renders it incapable of encoding scene-specific constrains. In this work, we propose the VLocNet++ architecture that employs a multitask learning approach to exploit the inter-task relationship between learning semantics, regressing 6-DoF global pose a…
