AI 中文总结
针对低光图像增强中生成式迁移易改变几何与色彩、固定色彩坐标影响梯度的问题，提出SA-RF与可学习Box-Cox极坐标颜色空间BC-IHV，在LOL基准等测试中优于现有最优方法，验证了所提框架与颜色表示的有效性。
AI 中文摘要
低光图像增强（LLIE）必须在不破坏输入图像已有结构的前提下修正模糊的曝光问题。生成式迁移可对曝光模糊进行建模，但其灵活性也可能改变可观测的几何结构和色彩内容。此外，固定的可逆色彩坐标通常仅被视为表示形式，尽管它们的逆映射会改变增强网络接收到的RGB域梯度。为解决这些问题，我们提出结构锚定整流流（SA-RF），其通过独立的色度/强度分支、尺度匹配的条件金字塔以及混合自适应层归一化（HybridAda）保持对应关系。HybridAda将空间交叉注意力的位置特定检索与池化自适应层归一化（AdaLN）的全局曝光调制相结合。我们进一步引入BC-IHV，一种可学习的Box-Cox极坐标颜色空间，其解析可逆的强度映射通过单个指数控制逆梯度动态范围，使该表示能平衡暗区扩展与梯度调节，而非采用固定的线性或对数规律。在三个LOL基准、盲图像质量评估及跨数据集测试上的实验表明，与现有最优方法（SOTA）相比，该方法具有一致的重建和感知优势。受控研究进一步验证了所提框架和颜色表示的有效性。
英文摘要
Low-light image enhancement (LLIE) must correct ambiguous exposure without overwriting structure already supported by the input. Generative transport can model exposure ambiguity; however, its flexibility may also alter observable geometry and chromatic content. Moreover, fixed invertible color coordinates are usually treated only as representations, although their inverse mappings reshape the RGB-domain gradients received by the enhancement network. To address these issues, we propose Structure-Anchored Rectified Flow (SA-RF), which maintains correspondence through separate chromaticity/intensity stems, a scale-matched condition pyramid, and HybridAda. HybridAda assigns location-specific retrieval to spatial cross-attention and global exposure modulation to pooled AdaLN. We further introduce BC-IHV, a learnable Box--Cox polar color space whose analytically invertible intensity mapping controls the inverse-gradient dynamic range through a single exponent. This allows the representation to balance dark-range expansion and gradient conditioning instead of adopting a fixed linear or logarithmic law. Experiments on three LOL benchmarks, blind image-quality evaluation, and cross-dataset tests demonstrate consistent reconstruction and perceptual advantages over the sota. Controlled studies further support the effectiveness of both the proposed framework and color representation.
Comments7 pages, 5 figures
