PANet: A Physics-guided Parametric Augmentation Net for Image Dehazing by Hazing

arXiv:2404.09269v1 Announce Type: new
Abstract: Image dehazing faces challenges when dealing with hazy images in real-world scenarios. A huge domain gap between synthetic and real-world haze images degrades dehazing performance in practical settings. However, collecting real-world image datasets for training dehazing models is challenging since both hazy and clean pairs must be captured under the same conditions. In this paper, we propose a Physics-guided Parametric Augmentation Network (PANet) that generates photo-realistic hazy and clean training pairs to effectively enhance real-world …

abstract arxiv augmentation challenges cs.cv datasets domain gap however image image datasets images parametric performance physics practical synthetic training type world