Equipping Diffusion Models with Differentiable Spatial Entropy for Low-Light Image Enhancement

arXiv:2404.09735v1 Announce Type: new
Abstract: Image restoration, which aims to recover high-quality images from their corrupted counterparts, often faces the challenge of being an ill-posed problem that allows multiple solutions for a single input. However, most deep learning based works simply employ l1 loss to train their network in a deterministic way, resulting in over-smoothed predictions with inferior perceptual quality. In this work, we propose a novel method that shifts the focus from a deterministic pixel-by-pixel comparison to a statistical …

arxiv cs.cv differentiable diffusion diffusion models entropy image light low spatial type