retinex-theory

[CVPR 2026] Multinex: Lightweight Low-light Image Enhancement via Multi-prior Retinex

M2Retinexformer: Multi-Modal Retinexformer for Low-Light Image Enhancement [IEEE ICIP 2026] is a novel framework that extends Retinexformer by incorporating depth cues, luminance priors, and semantic features within a progressive refinement pipeline.

Aether enhances low-light images from the PSR regions of lunar craters to improve signal-to-noise ratio (SNR). By applying advanced deep learning and image processing techniques, the project creates high-resolution image maps from Chandrayaan-2's OHRC, aiding lunar landing site selection and supporting geomorphological studies of the lunar pole

REGULATED SINGLE SCALE RETINEX ALGORITHM for nighttime image enhancement

Retinex in Matlab