Bi-Bridge：面向低光照图像增强的双向扩散桥
Bi-Bridge: Bidirectional Diffusion Bridges for Low-Light Image Enhancement
把增强与退化建模成同一个对称扩散桥的两个方向，用双向一致性作为内容保真的约束；做低光照增强、去噪、去模糊等图像到图像复原时，可借鉴这种「正反过程共享结构」的正则思路来抑制生成模型的结构漂移。
原文依据 models both enhancement and its inverse degradation within a single symmetric diffusion bridge
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论低光照图像增强（LLIE）是一项具有挑战性的任务，因为严重的信息丢失意味着单一输入可能对应多种合理的复原结果。这种固有的歧义使传统的基于回归的模型产生过度平滑、缺乏细节的结果。尽管近期的生成模型能够生成更丰富的细节，但其常见的单向设计往往会扭曲原始结构，从而损害内容保真度。我们提出 Bi-Bridge，一个统一的框架，在单个对称扩散桥中同时建模增强及其逆向退化。通过迫使网络在两种变换中均保持关键的内容结构，这种双向学习充当了强有力的约束，从而带来显著更忠实、更真实的复原结果。大量实验表明，Bi-Bridge 在多个基准上优于最优方法，为保真度与感知质量确立了新的标准。
英文原文摘要 984 字符
Low-Light Image Enhancement (LLIE) is a challenging task, as severe information loss means a single input can correspond to multiple plausible restorations. This inherent ambiguity causes conventional regression-based models to produce overly-smooth results that lack detail. While recent generative models can create richer details, their common unidirectional design often compromises content fidelity by distorting original structures. We introduce Bi-Bridge, a unified framework that models both enhancement and its inverse degradation within a single symmetric diffusion bridge. By compelling the network to preserve essential content structures across both transformations, this bidirectional learning acts as a powerful constraint, leading to significantly more faithful and realistic restorations. Extensive experiments show that Bi-Bridge outperforms state-of-the-art (SOTA) methods across multiple benchmarks, establishing a new standard for fidelity and perceptual quality.