中文
相关论文

相关论文: Deformable Convolutions and LSTM-based Flexible Ev…

200 篇论文

Recent work has shown impressive results on data-driven defocus deblurring using the two-image views available on modern dual-pixel (DP) sensors. One significant challenge in this line of research is access to DP data. Despite many cameras…

图像与视频处理 · 电气工程与系统科学 2021-08-18 Abdullah Abuolaim , Mauricio Delbracio , Damien Kelly , Michael S. Brown , Peyman Milanfar

Visual Deformation Measurement (VDM) aims to recover dense deformation fields by tracking surface motion from camera observations. Traditional image-based methods rely on minimal inter-frame motion to constrain the correspondence search…

计算机视觉与模式识别 · 计算机科学 2026-02-17 Yuliang Wu , Wei Zhai , Yuxin Cui , Tiesong Zhao , Yang Cao , Zheng-Jun Zha

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…

计算机视觉与模式识别 · 计算机科学 2021-08-27 Hyeongseok Son , Junyong Lee , Jonghyeop Lee , Sunghyun Cho , Seungyong Lee

Event cameras are bio-inspired sensors that offer advantages over traditional cameras. They operate asynchronously, sampling the scene at microsecond resolution and producing a stream of brightness changes. This unconventional output has…

计算机视觉与模式识别 · 计算机科学 2022-09-14 Suman Ghosh , Guillermo Gallego

Event camera sensors are bio-inspired sensors which asynchronously capture per-pixel brightness changes and output a stream of events encoding the polarity, location and time of these changes. These systems are witnessing rapid advancements…

计算机视觉与模式识别 · 计算机科学 2025-09-15 Aupendu Kar , Vishnu Raj , Guan-Ming Su

Clear imaging under hazy conditions is a critical task. Prior-based and neural methods have improved results. However, they operate on RGB frames, which suffer from limited dynamic range. Therefore, dehazing remains ill-posed and can erase…

计算机视觉与模式识别 · 计算机科学 2025-11-18 Ling Wang , Yunfan Lu , Wenzong Ma , Huizai Yao , Pengteng Li , Hui Xiong

Moving Object Detection (MOD) is a critical vision task for successfully achieving safe autonomous driving. Despite plausible results of deep learning methods, most existing approaches are only frame-based and may fail to reach reasonable…

计算机视觉与模式识别 · 计算机科学 2023-03-10 Zhuyun Zhou , Zongwei Wu , Rémi Boutteau , Fan Yang , Cédric Demonceaux , Dominique Ginhac

Video frame prediction extrapolates future frames from previous frames, but suffers from prediction errors in dynamic scenes due to the lack of information about the next frame. Event cameras address this limitation by capturing per-pixel…

计算机视觉与模式识别 · 计算机科学 2025-12-22 Jiyun Kong , Jun-Hyuk Kim , Jong-Seok Lee

Event cameras encode visual information with high temporal precision, low data-rate, and high-dynamic range. Thanks to these characteristics, event cameras are particularly suited for scenarios with high motion, challenging lighting…

计算机视觉与模式识别 · 计算机科学 2020-12-10 Etienne Perot , Pierre de Tournemire , Davide Nitti , Jonathan Masci , Amos Sironi

Continuous video monitoring in surveillance, robotics, and wearable systems faces a fundamental power constraint: conventional RGB cameras consume substantial energy through fixed-rate capture. Event cameras offer sparse, motion-driven…

计算机视觉与模式识别 · 计算机科学 2025-12-08 Dmitrii Torbunov , Onur Okuducu , Yi Huang , Odera Dim , Rebecca Coles , Yonggang Cui , Yihui Ren

Light field (LF) cameras can record scenes from multiple perspectives, and thus introduce beneficial angular information for image super-resolution (SR). However, it is challenging to incorporate angular information due to disparities among…

图像与视频处理 · 电气工程与系统科学 2020-12-30 Yingqian Wang , Jungang Yang , Longguang Wang , Xinyi Ying , Tianhao Wu , Wei An , Yulan Guo

The paper addresses the problem of acquiring high-quality photographs with handheld smartphone cameras in low-light imaging conditions. We propose an approach based on capturing pairs of short and long exposure images in rapid succession…

计算机视觉与模式识别 · 计算机科学 2020-09-03 Janne Mustaniemi , Juho Kannala , Jiri Matas , Simo Särkkä , Janne Heikkilä

Due to the extremely low latency, events have been recently exploited to supplement lost information for motion deblurring. Existing approaches largely rely on the perfect pixel-wise alignment between intensity images and events, which is…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Mingyuan Lin , Chi Zhang , Chu He , Lei Yu

Motion blur from camera shake is a major problem in videos captured by hand-held devices. Unlike single-image deblurring, video-based approaches can take advantage of the abundant information that exists across neighboring frames. As a…

计算机视觉与模式识别 · 计算机科学 2016-11-28 Shuochen Su , Mauricio Delbracio , Jue Wang , Guillermo Sapiro , Wolfgang Heidrich , Oliver Wang

Video deblurring is essential task for autonomous driving, facial recognition, and security surveillance. Traditional methods directly estimate motion blur kernels, often introducing artifacts and leading to poor results. Recent approaches…

计算机视觉与模式识别 · 计算机科学 2025-01-22 Yang Tian , Fabio Brau , Giulio Rossolini , Giorgio Buttazzo , Hao Meng

Recently, deep learning based image deblurring has been well developed. However, exploiting the detailed image features in a deep learning framework always requires a mass of parameters, which inevitably makes the network suffer from high…

计算机视觉与模式识别 · 计算机科学 2026-01-28 Yanni Zhang , Yiming Liu , Qiang Li , Miao Qi , Dahong Xu , Jun Kong , Jianzhong Wang

Modern vehicles are equipped with various driver-assistance systems, including automatic lane keeping, which prevents unintended lane departures. Traditional lane detection methods incorporate handcrafted or deep learning-based features…

计算机视觉与模式识别 · 计算机科学 2021-12-01 Farzeen Munir , Shoaib Azam , Moongu Jeon , Byung-Geun Lee , Witold Pedrycz

Diffusion models have achieved significant progress in image generation. The pre-trained Stable Diffusion (SD) models are helpful for image deblurring by providing clear image priors. However, directly using a blurry image or pre-deblurred…

计算机视觉与模式识别 · 计算机科学 2025-02-07 Lingshun Kong , Jiawei Zhang , Dongqing Zou , Jimmy Ren , Xiaohe Wu , Jiangxin Dong , Jinshan Pan

Existing RGB-Event visual object tracking approaches primarily rely on conventional feature-level fusion, failing to fully exploit the unique advantages of event cameras. In particular, the high dynamic range and motion-sensitive nature of…

计算机视觉与模式识别 · 计算机科学 2026-01-06 Shiao Wang , Xiao Wang , Haonan Zhao , Jiarui Xu , Bo Jiang , Lin Zhu , Xin Zhao , Yonghong Tian , Jin Tang

Most motion deblurring algorithms rely on spatial-domain convolution models, which struggle with the complex, non-linear blur arising from camera shake and object motion. In contrast, we propose a novel single-image deblurring approach that…

图像与视频处理 · 电气工程与系统科学 2025-01-23 Wang Pang , Zhihao Zhan , Xiang Zhu , Yechao Bai