无需配对数据，实现低光视频时序一致增强
Zero-TIG: Temporal Consistency-Aware Zero-Shot Illumination-Guided Low-light Video Enhancement
- 基于Retinex理论与光流技术，分三步提升图像质量
- 通过帧间对齐保持视频时序连续性，有效减少闪烁
- 适合真实场景中无标注数据的低光视频增强
低光与水下视频普遍存在可视性差、对比度低和噪声大等问题，亟需视觉质量增强。现有方法多依赖成对真实数据，实用性受限且难以保证时序一致性。为此，本文提出一种新颖的零样本学习方法Zero-TIG，结合Retinex理论与光流技术。网络包含增强模块与时序反馈模块：增强模块由低光图像去噪、光照估计和反射去噪三个子网络组成；时序反馈模块通过直方图均衡化、光流计算与图像形变，将前一帧增强结果对齐当前帧，确保时序连续性。同时，针对水下数据颜色失真问题，采用自适应平衡RGB通道。实验表明，该方法无需配对训练数据即可实现低光视频增强，具备良好的实际应用前景。
原文摘要 · Abstract (English)
Low-light and underwater videos suffer from poor visibility, low contrast, and high noise, necessitating enhancements in visual quality. However, existing approaches typically rely on paired ground truth, which limits their practicality and often fails to maintain temporal consistency. To overcome these obstacles, this paper introduces a novel zero-shot learning approach named Zero-TIG, leveraging the Retinex theory and optical flow techniques. The proposed network consists of an enhancement module and a temporal feedback module. The enhancement module comprises three subnetworks: low-light image denoising, illumination estimation, and reflection denoising. The temporal enhancement module ensures temporal consistency by incorporating histogram equalization, optical flow computation, and image warping to align the enhanced previous frame with the current frame, thereby maintaining continuity. Additionally, we address color distortion in underwater data by adaptively balancing RGB channels. The experimental results demonstrate that our method achieves low-light video enhancement without the need for paired training data, making it a promising and applicable method for real-world scenario enhancement.
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。