分离光照结构与曝光水平，实现自适应低光增强。
Learning Structural Illumination for Unsupervised Low-light Enhancement
- 将光照结构从整体曝光中解耦，基于明亮区域估计。
- 在多个数据集上优于现有无监督方法，视觉效果自然。
- 适合需要自适应光照调整的图像增强场景。
现有无监督低光图像增强（LLIE）方法通常直接从整幅低光输入中估计光照，未分离空间变化的光照结构（相对光照结构）与绝对曝光水平，且未排除信噪比低区域对估计的干扰。此外，固定曝光目标导致场景无关的增强准则，限制了在多样光照条件下的适应能力。受光的空间传播启发，本文提出相对光照结构估计（RISE）框架，将相对光照结构与绝对曝光解耦，并基于可靠亮区进行推断，实现可解释且鲁棒的增强。为进一步实现场景自适应曝光调整，提出基于每张输入图像的双测光曝光参考，使RISE能根据具体场景调节增强强度，在多样化光照条件下实现良好泛化。大量基准测试与真实世界泛化实验表明，RISE在无监督LLIE方法中达到领先性能，同时生成视觉自然的结果。
原文摘要 · Abstract (English)
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.
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。