Video Dehazing via a Multi-Range Temporal Alignment Network with Physical Prior
This work addresses the problem of improving visibility in hazy videos for applications like surveillance and autonomous driving, representing an incremental advance with a new dataset.
The paper tackles video dehazing by developing a framework that integrates physical haze priors and multi-range temporal alignment, resulting in superior performance on synthetic and real-world benchmarks.
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.