Skip to yearly menu bar Skip to main content


Zero-Reference Low-Light Enhancement via Physical Quadruple Priors

Wenjing Wang · Huan Yang · Jianlong Fu · Jiaying Liu

Arch 4A-E Poster #185
[ ] [ Project Page ]
Fri 21 Jun 5 p.m. PDT — 6:30 p.m. PDT


Understanding illumination and reducing the need for supervision pose a significant challenge in low-light enhancement. Current approaches are highly sensitive to data usage during training and illumination-specific hyper-parameters, limiting their ability to handle unseen scenarios.In this paper, we propose a new zero-reference low-light enhancement framework trainable solely with normal light images. To accomplish this, we devise an illumination-invariant prior inspired by the theory of physical light transfer. This prior serves as the bridge between normal and low-light images.Then, we develop a prior-to-image framework trained without low-light data.During testing, this framework is able to restore our illumination-invariant prior back to images, automatically achieving low-light enhancement.Within this framework, we leverage a pretrained generative diffusion model for model ability, introduce a bypass decoder to handle detail distortion, as well as offer a lightweight version for practicality.Extensive experiments demonstrate our framework's superiority in various scenarios as well as good interpretability, robustness, and efficiency. Code will be released after the review process.

Live content is unavailable. Log in and register to view live content