无需配对数据，提升低光视频在多变光照下的时序一致性
TempRetinex: Retinex-based Unsupervised Enhancement for Low-light Video Under Diverse Lighting Conditions
- 基于Retinex原理，利用帧间相关性进行无监督增强
- 在多个数据集上实现最优感知质量，显著改善光影变化下的稳定性
- 适合处理复杂光照环境下的视频修复与增强任务
由于低光视频序列缺乏配对数据，存在时间不一致、光照特性差异和相机参数变化等问题，无监督低光增强方法受到广泛关注。本文提出TempRetinex，一种基于Retinex的无监督视频增强框架，利用帧间相关性建模。引入亮度一致性预处理（BCP），显式对齐不同曝光下的强度分布，显著提升模型在多样光照场景下的鲁棒性。设计多尺度时序一致性损失与遮挡感知掩码技术，强化相邻帧间相似性。进一步采用反向推理（RI）策略优化时间不稳定帧，并引入自集成（SE）机制提升复杂纹理下的去噪能力。实验表明，TempRetinex在感知质量方面达到当前最优水平。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。