arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.09757cs.CV
收藏

基于物理先验的多范围时间对齐网络的视频去雾

Video Dehazing via a Multi-Range Temporal Alignment Network with Physical Prior

The Chinese University of Hong Kong(香港中文大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));The Hong Kong University of Science and Technology(香港科技大学);Tsinghua University(清华大学)

Jiaqi Xu, Xiaowei Hu, Lei Zhu, Qi Dou, Jifeng Dai, Yu Qiao, Pheng-Ann Heng

摘要:

视频去雾旨在恢复具有高可见度和对比度的无雾帧。本文提出了一种新的框架,有效地探索物理霾先验和聚合时间信息。具体来说,我们设计了一个基于记忆的物理先验指导模块,将先验相关特征编码到远程记忆中。此外,我们制定了一个多范围的场景辐射恢复模块,以捕捉在多个时空范围的时空依赖性,这有助于有效地聚合从相邻帧的时间信息。此外,我们构建了第一个大规模的户外视频去雾基准数据集,其中包含各种真实场景中的视频。仿真和实际实验结果表明了该方法的优越性。

英文摘要:

Video dehazing aims to recover haze-free frames with high visibility and contrast. This paper presents a novel framework to effectively explore the physical haze priors and aggregate temporal information. Specifically, we design a memory-based physical prior guidance module to encode the prior-related features into long-range memory. Besides, we formulate a multi-range scene radiance recovery module to capture space-time dependencies in multiple space-time ranges, which helps to effectively aggregate temporal information from adjacent frames. Moreover, we construct the first large-scale outdoor video dehazing benchmark dataset, which contains videos in various real-world scenarios. Experimental results on both synthetic and real conditions show the superiority of our proposed method.

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。

↑