{"ID":2842962,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.09609","arxiv_id":"2511.09609","title":"TempRetinex: Retinex-based Unsupervised Enhancement for Low-light Video Under Diverse Lighting Conditions","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) mechanism to boost denoising across diverse textures. Experiments demonstrate that TempRetinex achieves state-of-the-art performance in perceptual quality.","short_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...","url_abs":"https://arxiv.org/abs/2511.09609","url_pdf":"https://arxiv.org/pdf/2511.09609v2","authors":"[\"Yini Li\",\"Louis Forster\",\"David Bull\",\"Nantheera Anantrasirichai\"]","published":"2025-11-12T18:38:53Z","proceeding":"eess.IV","tasks":"[\"eess.IV\"]","methods":"[]","has_code":false}