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

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.

Cite

Text

Xu et al. "Video Dehazing via a Multi-Range Temporal Alignment Network with Physical Prior." Conference on Computer Vision and Pattern Recognition, 2023. doi:10.1109/CVPR52729.2023.01731

Markdown

[Xu et al. "Video Dehazing via a Multi-Range Temporal Alignment Network with Physical Prior." Conference on Computer Vision and Pattern Recognition, 2023.](https://mlanthology.org/cvpr/2023/xu2023cvpr-video/) doi:10.1109/CVPR52729.2023.01731

BibTeX

@inproceedings{xu2023cvpr-video,
  title     = {{Video Dehazing via a Multi-Range Temporal Alignment Network with Physical Prior}},
  author    = {Xu, Jiaqi and Hu, Xiaowei and Zhu, Lei and Dou, Qi and Dai, Jifeng and Qiao, Yu and Heng, Pheng-Ann},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2023},
  pages     = {18053-18062},
  doi       = {10.1109/CVPR52729.2023.01731},
  url       = {https://mlanthology.org/cvpr/2023/xu2023cvpr-video/}
}