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

Jiaqi Xu, Xiaowei Hu, Lei Zhu, Qi Dou, Jifeng Dai, Yu Qiao, Pheng-Ann Heng; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 18053-18062

Abstract

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.

Related Material

[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Jiaqi and Hu, Xiaowei and Zhu, Lei and Dou, Qi and Dai, Jifeng and Qiao, Yu and Heng, Pheng-Ann}, title = {Video Dehazing via a Multi-Range Temporal Alignment Network With Physical Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18053-18062} }