中文
相关论文

相关论文: Restoring Real-World Degraded Events Improves Debl…

200 篇论文

State-of-the-art video deblurring methods cannot handle blurry videos recorded in dynamic scenes, since they are built under a strong assumption that the captured scenes are static. Contrary to the existing methods, we propose a video…

计算机视觉与模式识别 · 计算机科学 2016-03-15 Tae Hyun Kim , Seungjun Nah , Kyoung Mu Lee

Event cameras are emerging imaging technology that offers advantages over conventional frame-based imaging sensors in dynamic range and sensing speed. Complementing the rich texture and color perception of traditional image frames, the…

计算机视觉与模式识别 · 计算机科学 2023-12-14 Peiqi Duan , Boyu Li , Yixin Yang , Hanyue Lou , Minggui Teng , Yi Ma , Boxin Shi

Deblurring can not only provide visually more pleasant pictures and make photography more convenient, but also can improve the performance of objection detection as well as tracking. However, removing dynamic scene blur from images is a…

计算机视觉与模式识别 · 计算机科学 2023-01-19 Jiawei Zhang , Jinshan Pan , Daoye Wang , Shangchen Zhou , Xing Wei , Furong Zhao , Jianbo Liu , Jimmy Ren

Achieving sharp 3D reconstruction from motion-blurred images alone becomes challenging, motivating recent methods to incorporate event cameras, benefiting from microsecond temporal resolution. However, they suffer from residual artifacts…

计算机视觉与模式识别 · 计算机科学 2026-04-27 Feiyu An , Yufei Deng , Zihui Zhang , Rong Xiao

Image deblurring, a.k.a. image deconvolution, recovers a clear image from pixel superposition caused by blur degradation. Few deep convolutional neural networks (CNN) succeed in addressing this task. In this paper, we first demonstrate that…

计算机视觉与模式识别 · 计算机科学 2018-11-06 Li Si-Yao , Dongwei Ren , Furong Zhao , Zijian Hu , Junfeng Li , Qian Yin

Nowadays stereo cameras are more commonly adopted in emerging devices such as dual-lens smartphones and unmanned aerial vehicles. However, they also suffer from blurry images in dynamic scenes which leads to visual discomfort and hampers…

计算机视觉与模式识别 · 计算机科学 2019-04-11 Shangchen Zhou , Jiawei Zhang , Wangmeng Zuo , Haozhe Xie , Jinshan Pan , Jimmy Ren

Under-display camera (UDC) systems are the foundation of full-screen display devices in which the lens mounts under the display. The pixel array of light-emitting diodes used for display diffracts and attenuates incident light, causing…

计算机视觉与模式识别 · 计算机科学 2024-03-12 Chengxu Liu , Xuan Wang , Yuanting Fan , Shuai Li , Xueming Qian

Event cameras offer significant advantages for low-light video enhancement, primarily due to their high dynamic range. Current research, however, is severely limited by the absence of large-scale, real-world, and spatio-temporally aligned…

计算机视觉与模式识别 · 计算机科学 2024-08-30 Kanghao Chen , Guoqiang Liang , Hangyu Li , Yunfan Lu , Lin Wang

Present-day deep learning-based motion deblurring methods utilize the pair of synthetic blur and sharp data to regress any particular framework. This task is designed for directly translating a blurry image input into its restored version…

计算机视觉与模式识别 · 计算机科学 2021-11-29 Jonathan Samuel Lumentut , In Kyu Park

Dynamic scene video deblurring aims to remove undesirable blurry artifacts captured during the exposure process. Although previous video deblurring methods have achieved impressive results, they suffer from significant performance drops due…

计算机视觉与模式识别 · 计算机科学 2024-07-15 Jin-Ting He , Fu-Jen Tsai , Jia-Hao Wu , Yan-Tsung Peng , Chung-Chi Tsai , Chia-Wen Lin , Yen-Yu Lin

High dynamic range imaging (HDRI) for real-world dynamic scenes is challenging because moving objects may lead to hybrid degradation of low dynamic range and motion blur. Existing event-based approaches only focus on a separate task, while…

计算机视觉与模式识别 · 计算机科学 2024-04-05 Li Xiaopeng , Zeng Zhaoyuan , Fan Cien , Zhao Chen , Deng Lei , Yu Lei

Reconstructing sharp 3D representations from blurry multi-view images are long-standing problem in computer vision. Recent works attempt to enhance high-quality novel view synthesis from the motion blur by leveraging event-based cameras,…

计算机视觉与模式识别 · 计算机科学 2025-04-01 Seungjun Lee , Gim Hee Lee

Image deblurring is a fundamental and challenging low-level vision problem. Previous vision research indicates that edge structure in natural scenes is one of the most important factors to estimate the abilities of human visual perception.…

计算机视觉与模式识别 · 计算机科学 2020-07-14 Zhichao Fu , Tianlong Ma , Yingbin Zheng , Hao Ye , Jing Yang , Liang He

Even though the collaboration between traditional and neuromorphic event cameras brings prosperity to frame-event based vision applications, the performance is still confined by the resolution gap crossing two modalities in both spatial and…

计算机视觉与模式识别 · 计算机科学 2023-10-02 Chi Zhang , Xiang Zhang , Mingyuan Lin , Cheng Li , Chu He , Wen Yang , Gui-Song Xia , Lei Yu

Currently, methods for single-image deblurring based on CNNs and transformers have demonstrated promising performance. However, these methods often suffer from perceptual limitations, poor generalization ability, and struggle with heavy or…

计算机视觉与模式识别 · 计算机科学 2025-03-11 Xiaoyang Liu , Yuquan Wang , Zheng Chen , Jiezhang Cao , He Zhang , Yulun Zhang , Xiaokang Yang

Motion blur is a fundamental problem in computer vision as it impacts image quality and hinders inference. Traditional deblurring algorithms leverage the physics of the image formation model and use hand-crafted priors: they usually produce…

计算机视觉与模式识别 · 计算机科学 2018-01-17 Huaijin Chen , Jinwei Gu , Orazio Gallo , Ming-Yu Liu , Ashok Veeraraghavan , Jan Kautz

3D reconstruction methods such as 3D Gaussian Splatting (3DGS) and Neural Radiance Fields (NeRF) achieve impressive photorealism but fail when input images suffer from severe motion blur. While event cameras provide high-temporal-resolution…

计算机视觉与模式识别 · 计算机科学 2026-05-11 Jun Dai , Renbiao Jin , Bo Xu , Yutian Chen , Linning Xu , Mulin Yu , Tianfan Xue , Shi Guo

Successfully training end-to-end deep networks for real motion deblurring requires datasets of sharp/blurred image pairs that are realistic and diverse enough to achieve generalization to real blurred images. Obtaining such datasets remains…

计算机视觉与模式识别 · 计算机科学 2025-04-03 Guillermo Carbajal , Patricia Vitoria , José Lezama , Pablo Musé

Current video deblurring methods have limitations in recovering high-frequency information since the regression losses are conservative with high-frequency details. Since Diffusion Models (DMs) have strong capabilities in generating…

计算机视觉与模式识别 · 计算机科学 2024-08-27 Chen Rao , Guangyuan Li , Zehua Lan , Jiakai Sun , Junsheng Luan , Wei Xing , Lei Zhao , Huaizhong Lin , Jianfeng Dong , Dalong Zhang

Video restoration task aims to recover high-quality videos from low-quality observations. This contains various important sub-tasks, such as video denoising, deblurring and low-light enhancement, since video often faces different types of…

计算机视觉与模式识别 · 计算机科学 2024-01-29 Yuxiang Hui , Yang Liu , Yaofang Liu , Fan Jia , Jinshan Pan , Raymond Chan , Tieyong Zeng