PIE: Physics-inspired Low-light Enhancement

arXiv:2404.04586v1 Announce Type: new
Abstract: In this paper, we propose a physics-inspired contrastive learning paradigm for low-light enhancement, called PIE. PIE primarily addresses three issues: (i) To resolve the problem of existing learning-based methods often training a LLE model with strict pixel-correspondence image pairs, we eliminate the need for pixel-correspondence paired training data and instead train with unpaired images. (ii) To address the disregard for negative samples and the inadequacy of their generation in existing methods, we incorporate physics-inspired contrastive …

abstract arxiv cs.cv data image light low paper paradigm physics pixel train training training data type