Skip to yearly menu bar Skip to main content


Poster

Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance

Junkai Fan · Jiangwei Weng · Kun Wang · Yijun Yang · Jianjun Qian · Jun Li · Jian Yang

Arch 4A-E Poster #190
[ ] [ Project Page ]
[ Poster
Fri 21 Jun 5 p.m. PDT — 6:30 p.m. PDT

Abstract:

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 non-aligned 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 multi-frame 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.

Chat is not available.