English
Related papers

Related papers: Learning Physical-Spatio-Temporal Features for Vid…

200 papers

Visual-based perception is the key module for autonomous driving. Among those visual perception tasks, video object detection is a primary yet challenging one because of feature degradation caused by fast motion or multiple poses. Current…

Computer Vision and Pattern Recognition · Computer Science 2024-05-30 Yiming Cui , Cheng Han , Dongfang Liu

Despite the success of deep learning for static image understanding, it remains unclear what are the most effective network architectures for the spatial-temporal modeling in videos. In this paper, in contrast to the existing CNN+RNN or…

Computer Vision and Pattern Recognition · Computer Science 2018-12-12 Dongliang He , Zhichao Zhou , Chuang Gan , Fu Li , Xiao Liu , Yandong Li , Limin Wang , Shilei Wen

We present a diffusion-based portrait shadow removal approach that can robustly produce high-fidelity results. Unlike previous methods, we cast shadow removal as diffusion-based inpainting. To this end, we first train a shadow-independent…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 Wanchang Yu , Qing Zhang , Rongjia Zheng , Wei-Shi Zheng

Removing objects from images is a challenging problem that is important for many applications, including mixed reality. For believable results, the shadows that the object casts should also be removed. Current inpainting-based methods only…

Computer Vision and Pattern Recognition · Computer Science 2020-12-22 Edward Zhang , Ricardo Martin-Brualla , Janne Kontkanen , Brian Curless

The success of deep neural networks generally requires a vast amount of training data to be labeled, which is expensive and unfeasible in scale, especially for video collections. To alleviate this problem, in this paper, we propose…

Computer Vision and Pattern Recognition · Computer Science 2019-04-05 Longlong Jing , Xiaodong Yang , Jingen Liu , Yingli Tian

We propose a Spatiotemporal Sampling Network (STSN) that uses deformable convolutions across time for object detection in videos. Our STSN performs object detection in a video frame by learning to spatially sample features from the adjacent…

Computer Vision and Pattern Recognition · Computer Science 2018-07-25 Gedas Bertasius , Lorenzo Torresani , Jianbo Shi

Removing objects from videos remains difficult in the presence of real-world imperfections such as shadows, abrupt motion, and defective masks. Existing diffusion-based video inpainting models often struggle to maintain temporal stability…

Computer Vision and Pattern Recognition · Computer Science 2026-04-23 Jiagao Hu , Yuxuan Chen , Fuhao Li , Zepeng Wang , Fei Wang , Daiguo Zhou , Jian Luan

In portraits, eyeglasses may occlude facial regions and generate cast shadows on faces, which degrades the performance of many techniques like face verification and expression recognition. Portrait eyeglasses removal is critical in handling…

Computer Vision and Pattern Recognition · Computer Science 2022-03-22 Junfeng Lyu , Zhibo Wang , Feng Xu

Facial shadows often degrade image quality and the performance of vision algorithms. Existing methods struggle to remove shadows while preserving texture, especially under complex lighting conditions, and they lack real-world paired…

Computer Vision and Pattern Recognition · Computer Science 2026-01-28 Tailong Luo , Jiesong Bai , Jinyang Huang , Junyu Xia , Wangyu Wu , Xuhang Chen

Image shadow removal is a typical low-level vision task. Shadows cause local brightness shifts, which reduce the performance of downstream vision tasks. Currently, Transformer-based shadow removal methods suffer from quadratic computational…

Computer Vision and Pattern Recognition · Computer Science 2025-08-11 Xiujin Zhu , Chee-Onn Chow , Joon Huang Chuah

Casually-taken portrait photographs often suffer from unflattering lighting and shadowing because of suboptimal conditions in the environment. Aesthetic qualities such as the position and softness of shadows and the lighting ratio between…

Computer Vision and Pattern Recognition · Computer Science 2020-05-21 Xuaner Cecilia Zhang , Jonathan T. Barron , Yun-Ta Tsai , Rohit Pandey , Xiuming Zhang , Ren Ng , David E. Jacobs

Visual surveillance aims to perform robust foreground object detection regardless of the time and place. Object detection shows good results using only spatial information, but foreground object detection in visual surveillance requires…

Computer Vision and Pattern Recognition · Computer Science 2022-09-20 Keong-Hun Choi , Jong-Eun Ha

Illumination effects in images, specifically cast shadows and shading, have been shown to decrease the performance of deep neural networks on a large number of vision-based detection, recognition and segmentation tasks in urban driving…

Computer Vision and Pattern Recognition · Computer Science 2019-09-27 Alexandra Carlson , Ram Vasudevan , Matthew Johnson-Roberson

Recent self-supervised video representation learning methods have found significant success by exploring essential properties of videos, e.g. speed, temporal order, etc. This work exploits an essential yet under-explored property of videos,…

Computer Vision and Pattern Recognition · Computer Science 2022-01-13 Hanwen Liang , Niamul Quader , Zhixiang Chi , Lizhe Chen , Peng Dai , Juwei Lu , Yang Wang

To facilitate video denoising research, we construct a compelling dataset, namely, "Practical Video Denoising Dataset" (PVDD), containing 200 noisy-clean dynamic video pairs in both sRGB and RAW format. Compared with existing datasets…

Computer Vision and Pattern Recognition · Computer Science 2022-12-02 Xiaogang Xu , Yitong Yu , Nianjuan Jiang , Jiangbo Lu , Bei Yu , Jiaya Jia

High-quality video inpainting that completes missing regions in video frames is a promising yet challenging task. State-of-the-art approaches adopt attention models to complete a frame by searching missing contents from reference frames,…

Computer Vision and Pattern Recognition · Computer Science 2020-07-21 Yanhong Zeng , Jianlong Fu , Hongyang Chao

Shadow removal is challenging due to the complex interaction of geometry, lighting, and environmental factors. Existing unsupervised methods often overlook shadow-specific priors, leading to incomplete shadow recovery. To address this…

Computer Vision and Pattern Recognition · Computer Science 2025-04-09 Tao Lin , Qingwang Wang , Qiwei Liang , Minghua Tang , Yuxuan Sun

Shadow, as a natural consequence of light interacting with objects, plays a crucial role in shaping the aesthetics of an image, which however also impairs the content visibility and overall visual quality. Recent shadow removal approaches…

Computer Vision and Pattern Recognition · Computer Science 2024-11-22 Hengxing Liu , Mingjia Li , Xiaojie Guo

Video prediction has been considered a difficult problem because the video contains not only high-dimensional spatial information but also complex temporal information. Video prediction can be performed by finding features in recent frames,…

Computer Vision and Pattern Recognition · Computer Science 2019-07-16 Jungbeom Lee , Jangho Lee , Sungmin Lee , Sungroh Yoon

In this report, our approach to tackling the task of ActivityNet 2018 Kinetics-600 challenge is described in detail. Though spatial-temporal modelling methods, which adopt either such end-to-end framework as I3D \cite{i3d} or two-stage…

Computer Vision and Pattern Recognition · Computer Science 2018-06-28 Dongliang He , Fu Li , Qijie Zhao , Xiang Long , Yi Fu , Shilei Wen