arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.10744cs.CV
收藏

CVPR 2024 PBDL挑战赛技术报告

Technique Report of CVPR 2024 PBDL Challenges

Beijing Institute of Technology(北京理工大学);International Digital Economy Academy(国际数字经济学院);Peking University(北京大学)
Ying Fu, Yu Li, Shaodi You, Boxin Shi, Linwei Chen, Yunhao Zou, Zichun Wang, Yichen Li, Yuze Han, Yingkai Zhang, Jianan Wang, Qinglin Liu, Wei Yu, Xiaoqian Lv, … 展开作者

Ying Fu, Yu Li, Shaodi You, Boxin Shi, Linwei Chen, Yunhao Zou, Zichun Wang, Yichen Li, Yuze Han, Yingkai Zhang, Jianan Wang, Qinglin Liu, Wei Yu, Xiaoqian Lv, Jianing Li, Shengping Zhang, Xiangyang Ji, Yuanpei Chen, Yuhan Zhang, Weihang Peng, Liwen Zhang, Zhe Xu, Dingyong Gou, Cong Li, Senyan Xu, Yunkang Zhang, Siyuan Jiang, Xiaoqiang Lu, Licheng Jiao, Fang Liu, Xu Liu, Lingling Li, Wenping Ma, Shuyuan Yang, Haiyang Xie, Jian Zhao, Shihua Huang, Peng Cheng, Xi Shen, Zheng Wang, Shuai An, Caizhi Zhu, Xuelong Li, Tao Zhang, Liang Li, Yu Liu, Chenggang Yan, Gengchen Zhang, Linyan Jiang, Bingyi Song, Zhuoyu An, Haibo Lei, Qing Luo, Jie Song, Yuan Liu, Qihang Li, Haoyuan Zhang, Lingfeng Wang, Wei Chen, Aling Luo, Cheng Li, Jun Cao, Shu Chen, Zifei Dou, Xinyu Liu, Jing Zhang, Kexin Zhang, Yuting Yang, Xuejian Gou, Qinliang Wang, Yang Liu, Shizhan Zhao, Yanzhao Zhang, Libo Yan, Yuwei Guo, Guoxin Li, Qiong Gao, Chenyue Che, Long Sun, Xiang Chen, Hao Li, Jinshan Pan, Chuanlong Xie, Hongming Chen, Mingrui Li, Tianchen Deng, Jingwei Huang, Yufeng Li, Fei Wan, Bingxin Xu, Jian Cheng, Hongzhe Liu, Cheng Xu, Yuxiang Zou, Weiguo Pan, Songyin Dai, Sen Jia, Junpei Zhang, Puhua Chen, Qihang Li

AI总结:

本报告总结了CVPR 2024举办的PBDL 2024挑战赛成果,该赛事聚焦低光照增强检测与HDR成像共8个赛道,详述了各赛道的目标、方法与优胜方案的创新思路。

摘要:

基于物理的视觉与深度学习的交叉领域是推动计算机视觉技术发展的前沿方向。通过利用物理学原理指导并优化深度学习模型,我们能够开发出更鲁棒、更精准的视觉系统。基于物理的视觉旨在反转成像过程,从图像中恢复形状、反射率、光分布及介质属性等场景特性。近年来,深度学习在各类视觉任务上展现出可观的性能提升,与基于物理的视觉结合后,这类方法可进一步增强视觉系统的鲁棒性与准确性。本技术报告总结了在CVPR 2024研讨会上举办的Physics-Based Vision Meets Deep Learning(PBDL,基于物理的视觉与深度学习)2024挑战赛的成果。本次挑战赛共设8个赛道,聚焦低光照增强与检测以及高动态范围(HDR)成像两大方向。报告详述了各赛道的目标、方法与结果,重点介绍了排名领先的解决方案及其创新思路。

英文摘要:

The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies. By leveraging the principles of physics to inform and enhance deep learning models, we can develop more robust and accurate vision systems. Physics-based vision aims to invert the processes to recover scene properties such as shape, reflectance, light distribution, and medium properties from images. In recent years, deep learning has shown promising improvements for various vision tasks, and when combined with physics-based vision, these approaches can enhance the robustness and accuracy of vision systems. This technical report summarizes the outcomes of the Physics-Based Vision Meets Deep Learning (PBDL) 2024 challenge, held in CVPR 2024 workshop. The challenge consisted of eight tracks, focusing on Low-Light Enhancement and Detection as well as High Dynamic Range (HDR) Imaging. This report details the objectives, methodologies, and results of each track, highlighting the top-performing solutions and their innovative approaches.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑