TempRetinex: Retinex-based Unsupervised Enhancement for Low-light Video Under Diverse Lighting Conditions
Yini Li, Louis Forster, David Bull, Nantheera Anantrasirichai

TL;DR
TempRetinex is an unsupervised Retinex-based video enhancement framework that improves low-light video quality by exploiting inter-frame correlations and ensuring temporal consistency under diverse lighting conditions.
Contribution
It introduces a novel unsupervised approach with Brightness Consistency Preprocessing, temporal consistency loss, occlusion-aware masking, Reverse Inference, and Self-Ensemble mechanisms.
Findings
Achieves state-of-the-art perceptual quality in low-light video enhancement.
Improves robustness to diverse lighting scenarios through BCP.
Enhances temporal stability and denoising in low-light videos.
Abstract
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)…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
