中文
相关论文

相关论文: MODNet-V: Improving Portrait Video Matting via Bac…

200 篇论文

Video portrait segmentation (VPS), aiming at segmenting prominent foreground portraits from video frames, has received much attention in recent years. However, simplicity of existing VPS datasets leads to a limitation on extensive research…

计算机视觉与模式识别 · 计算机科学 2024-07-03 Tianshu Yu , Changqun Xia , Jia Li

Searching by image is popular yet still challenging due to the extensive interference arose from i) data variations (e.g., background, pose, visual angle, brightness) of real-world captured images and ii) similar images in the query…

计算机视觉与模式识别 · 计算机科学 2023-03-27 Mingqiang Wei , Qian Sun , Haoran Xie , Dong Liang , Fu Lee Wang

The estimation of the camera poses associated with a set of images commonly relies on feature matches between the images. In contrast, we are the first to address this challenge by using objectness regions to guide the pose estimation…

计算机视觉与模式识别 · 计算机科学 2022-07-22 Matteo Taiana , Matteo Toso , Stuart James , Alessio Del Bue

This paper applies the recent fast iterative neural network framework, Momentum-Net, using appropriate models to low-dose X-ray computed tomography (LDCT) image reconstruction. At each layer of the proposed Momentum-Net, the model-based…

图像与视频处理 · 电气工程与系统科学 2020-09-10 Siqi Ye , Yong Long , Il Yong Chun

Extracting accurate foregrounds from natural images benefits many downstream applications such as film production and augmented reality. However, the furry characteristics and various appearance of the foregrounds, e.g., animal and…

计算机视觉与模式识别 · 计算机科学 2021-10-28 Jizhizi Li , Jing Zhang , Stephen J. Maybank , Dacheng Tao

Most approaches for video frame interpolation require accurate dense correspondences to synthesize an in-between frame. Therefore, they do not perform well in challenging scenarios with e.g. lighting changes or motion blur. Recent deep…

计算机视觉与模式识别 · 计算机科学 2018-04-04 Simone Meyer , Abdelaziz Djelouah , Brian McWilliams , Alexander Sorkine-Hornung , Markus Gross , Christopher Schroers

In this paper, we introduce the Volumetric Relightable Morphable Model (VRMM), a novel volumetric and parametric facial prior for 3D face modeling. While recent volumetric prior models offer improvements over traditional methods like 3D…

计算机视觉与模式识别 · 计算机科学 2024-05-09 Haotian Yang , Mingwu Zheng , Chongyang Ma , Yu-Kun Lai , Pengfei Wan , Haibin Huang

Recently, trimap-free methods have drawn increasing attention in human video matting due to their promising performance. Nevertheless, these methods still suffer from the lack of deterministic foreground-background cues, which impairs their…

计算机视觉与模式识别 · 计算机科学 2025-03-04 Huayu Zhang , Dongyue Wu , Yuanjie Shao , Nong Sang , Changxin Gao

Although it has been widely discussed in video surveillance, background subtraction is still an open problem in the context of complex scenarios, e.g., dynamic backgrounds, illumination variations, and indistinct foreground objects. To…

计算机视觉与模式识别 · 计算机科学 2015-02-03 Liang Lin , Yuanlu Xu , Xiaodan Liang , Jianhuang Lai

Image classification models often demonstrate unstable performance in real-world applications due to variations in image information, driven by differing visual perspectives of subject objects and lighting discrepancies. To mitigate these…

计算机视觉与模式识别 · 计算机科学 2024-07-29 Yuze Zheng , Zixuan Li , Xiangxian Li , Jinxing Liu , Yuqing Wang , Xiangxu Meng , Lei Meng

Blind Face Restoration (BFR) aims to recover high-quality face images from low-quality ones and usually resorts to facial priors for improving restoration performance. However, current methods still suffer from two major difficulties: 1)…

计算机视觉与模式识别 · 计算机科学 2023-12-11 Yanjiang Yu , Puyang Zhang , Kaihao Zhang , Wenhan Luo , Changsheng Li , Ye Yuan , Guoren Wang

Consumer-grade camera systems often struggle to maintain stable image quality under complex illumination conditions such as low light, high dynamic range, and backlighting, as well as spatial color temperature variation. These issues lead…

计算机视觉与模式识别 · 计算机科学 2025-10-24 Fuchen Li , Yansong Du , Wenbo Cheng , Xiaoxia Zhou , Sen Yin

Video Moment Retrieval (VMR) is a task to localize the temporal moment in untrimmed video specified by natural language query. For VMR, several methods that require full supervision for training have been proposed. Unfortunately, acquiring…

计算机视觉与模式识别 · 计算机科学 2023-10-10 Minuk Ma , Sunjae Yoon , Junyeong Kim , Youngjoon Lee , Sunghun Kang , Chang D. Yoo

Estimating the depth of objects from a single image is a valuable task for many vision, robotics, and graphics applications. However, current methods often fail to produce accurate depth for objects in diverse scenes. In this work, we…

计算机视觉与模式识别 · 计算机科学 2023-06-09 Manel Baradad , Yuanzhen Li , Forrester Cole , Michael Rubinstein , Antonio Torralba , William T. Freeman , Varun Jampani

Object recognition is a fundamental problem in many video processing tasks, accurately locating seen objects at low computation cost paves the way for on-device video recognition. We propose PatchNet, an efficient convolutional neural…

计算机视觉与模式识别 · 计算机科学 2021-03-15 Huizi Mao , Sibo Zhu , Song Han , William J. Dally

Many recent studies leverage the pre-trained CLIP for text-video cross-modal retrieval by tuning the backbone with additional heavy modules, which not only brings huge computational burdens with much more parameters, but also leads to the…

计算机视觉与模式识别 · 计算机科学 2023-03-23 Siteng Huang , Biao Gong , Yulin Pan , Jianwen Jiang , Yiliang Lv , Yuyuan Li , Donglin Wang

Large-scale video generative models are trained on vast and diverse visual data, enabling them to internalize rich structural, semantic, and dynamic priors of the visual world. While these models have demonstrated impressive generative…

计算机视觉与模式识别 · 计算机科学 2026-03-16 Shenghe Zheng , Junpeng Jiang , Wenbo Li

Background music (BGM) can enhance the video's emotion. However, selecting an appropriate BGM often requires domain knowledge. This has led to the development of video-music retrieval techniques. Most existing approaches utilize pretrained…

多媒体 · 计算机科学 2023-09-19 Tianjun Mao , Shansong Liu , Yunxuan Zhang , Dian Li , Ying Shan

Scene background initialization allows the recovery of a clear image without foreground objects from a video sequence, which is generally the first step in many computer vision and video processing applications. The process may be strongly…

计算机视觉与模式识别 · 计算机科学 2018-05-18 Zhe Xu , Biao Min , Ray C. C. Cheung

Cross-modality recognition has many important applications in science, law enforcement and entertainment. Popular methods to bridge the modality gap include reducing the distributional differences of representations of different modalities,…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Xin Niu , Enyi Li , Jinchao Liu , Yan Wang , Margarita Osadchy , Yongchun Fang