The acquisition of paired low-light video sequences remains challenging due to issues associated with poor temporal consistency, varying illumination characteristics and camera parameters. This has driven significant interest in unsupervised low-light enhancement approaches. In this context, we propose TempRetinex, an unsupervised Retinex-based video enhancement framework exploiting inter-frame correlations. We introduce Brightness Consistency Preprocessing (BCP) that explicitly aligns intensity distributions across exposures. BCP is shown to significantly improve model robustness to diverse lighting scenarios. Moreover, we propose a multiscale temporal consistency-aware loss and an occlusion-aware masking technique to enforce similarity between consecutive frames. We further incorporate a Reverse Inference (RI) strategy to refine temporally unstable frames and a Self-Ensemble (SE) mechanism to boost denoising across diverse textures. Experiments demonstrate that TempRetinex achieves state-of-the-art performance in perceptual quality.
@article{arxiv.2511.09609,
title = {TempRetinex: Retinex-based Unsupervised Enhancement for Low-light Video Under Diverse Lighting Conditions},
author = {Yini Li and Louis Forster and David Bull and Nantheera Anantrasirichai},
journal= {arXiv preprint arXiv:2511.09609},
year = {2026}
}