Saved in:
Bibliographic Details
Main Authors: Fan, Junkai, Weng, Jiangwei, Wang, Kun, Yang, Yijun, Qian, Jianjun, Li, Jun, Yang, Jian
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.09996
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912265013297152
author Fan, Junkai
Weng, Jiangwei
Wang, Kun
Yang, Yijun
Qian, Jianjun
Li, Jun
Yang, Jian
author_facet Fan, Junkai
Weng, Jiangwei
Wang, Kun
Yang, Yijun
Qian, Jianjun
Li, Jun
Yang, Jian
contents Real driving-video dehazing poses a significant challenge due to the inherent difficulty in acquiring precisely aligned hazy/clear video pairs for effective model training, especially in dynamic driving scenarios with unpredictable weather conditions. In this paper, we propose a pioneering approach that addresses this challenge through a nonaligned regularization strategy. Our core concept involves identifying clear frames that closely match hazy frames, serving as references to supervise a video dehazing network. Our approach comprises two key components: reference matching and video dehazing. Firstly, we introduce a non-aligned reference frame matching module, leveraging an adaptive sliding window to match high-quality reference frames from clear videos. Video dehazing incorporates flow-guided cosine attention sampler and deformable cosine attention fusion modules to enhance spatial multiframe alignment and fuse their improved information. To validate our approach, we collect a GoProHazy dataset captured effortlessly with GoPro cameras in diverse rural and urban road environments. Extensive experiments demonstrate the superiority of the proposed method over current state-of-the-art methods in the challenging task of real driving-video dehazing. Project page.
format Preprint
id arxiv_https___arxiv_org_abs_2405_09996
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance
Fan, Junkai
Weng, Jiangwei
Wang, Kun
Yang, Yijun
Qian, Jianjun
Li, Jun
Yang, Jian
Computer Vision and Pattern Recognition
Real driving-video dehazing poses a significant challenge due to the inherent difficulty in acquiring precisely aligned hazy/clear video pairs for effective model training, especially in dynamic driving scenarios with unpredictable weather conditions. In this paper, we propose a pioneering approach that addresses this challenge through a nonaligned regularization strategy. Our core concept involves identifying clear frames that closely match hazy frames, serving as references to supervise a video dehazing network. Our approach comprises two key components: reference matching and video dehazing. Firstly, we introduce a non-aligned reference frame matching module, leveraging an adaptive sliding window to match high-quality reference frames from clear videos. Video dehazing incorporates flow-guided cosine attention sampler and deformable cosine attention fusion modules to enhance spatial multiframe alignment and fuse their improved information. To validate our approach, we collect a GoProHazy dataset captured effortlessly with GoPro cameras in diverse rural and urban road environments. Extensive experiments demonstrate the superiority of the proposed method over current state-of-the-art methods in the challenging task of real driving-video dehazing. Project page.
title Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.09996