发表机构
Tianjin University; Dunhuang Academy（天津大学; 敦煌研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对现有无监督弱光图像增强方法的缺陷，提出RISE框架解耦相对光照结构与绝对曝光，结合双测光曝光参考实现场景自适应，在无监督弱光增强任务中达到最优性能且结果自然。
AI 中文摘要
现有的无监督弱光图像增强（LLIE）方法通常直接从整个弱光输入中估计光照，未将其空间变化的光照模式（称为相对光照结构）与绝对曝光水平分离，也未防止不可靠的低信噪比区域对估计产生偏差。此外，固定的曝光目标采用与场景无关的增强准则，限制了其对不同光照条件的适应性。受光的空间传播启发，我们提出了相对光照结构估计（RISE）框架，该框架将相对光照结构与绝对曝光解耦，并从可靠的亮区推断该结构，从而实现可解释且鲁棒的增强。为实现场景自适应的曝光调整，我们进一步提出了从每个输入中推导的双测光曝光参考，使RISE能够将增强强度适配到单个场景，并在不同光照条件下实现泛化。大量基准测试和真实世界泛化实验表明，RISE在无监督LLIE方法中达到了最先进的性能，同时生成视觉自然的结果。
英文摘要
Existing unsupervised low-light image enhancement (LLIE) methods often estimate illumination directly from the entire low-light input, without separating its spatially varying illumination pattern, termed relative illumination structure, from the absolute exposure level or preventing unreliable low signal-to-noise ratio regions from biasing the estimate. Moreover, fixed exposure targets impose a scene-agnostic enhancement criterion, limiting adaptation across diverse lighting conditions. Inspired by the spatial propagation of light, we propose a Relative Illumination Structure Estimation (RISE) framework that decouples relative illumination structure from absolute exposure and infers it from reliable bright regions, enabling interpretable and robust enhancement. For scene-adaptive exposure adjustment, we further propose a Dual-Metering Exposure Reference derived from each input, allowing RISE to adapt the enhancement strength to individual scenes and generalize across diverse lighting conditions. Extensive benchmark and real-world generalization experiments show that RISE achieves state-of-the-art performance among unsupervised LLIE methods while producing visually natural results.
