针对纯色场景颜色恒常性难题，提出感知场景特征的调制网络与自学习色空间。
SAFE: Scene-Aware Feature Modulation for Color Constancy with Learned Color Space in Pure-Color Scenes
- 设计场景感知特征调制网络，将光照线索结构化为四令牌表示并动态重加权。
- 在纯色场景下，平均角度误差降低10%，前25%误差减少20%。
- 适合处理高饱和度、低纹理的纯色图像，如广告图、艺术作品等场景。
纯色场景下的颜色恒常性极具挑战：当多数像素集中在狭窄色相范围内时，所有基于色度的线索退化为单一点，导致标准估计器出现歧义。本文提出一个紧凑框架，融合两项创新：(i) SAFE——一种场景感知特征调制网络，将光照线索组织为结构化的四令牌表示，并根据场景复杂度特征进行选择性重加权；(ii) 学习色空间（LCS），一种依赖场景的色度归一化方法，直接解决纯色场景中的色度坍塌问题。实验表明，SAFE在纯色场景中持续提升性能：相比各指标最佳基线，平均角度误差降低10%，前25%误差下降20%，后25%误差减少5.8%。
原文摘要 · Abstract (English)
Color constancy on pure-color scenes is challenging: when most pixels share a narrow band of hues, every chromaticity-based cue collapses to a single point and standard estimators become ambiguous. We propose a compact framework that couples two innovations: (i) SAFE, a Scene-Aware FeaturE modulation network that organizes illumination cues into a structured four-token representation, which is then selectively reweighted based on scene complexity features; (ii) the Learned Color Space (LCS), a scene-dependent chromaticity normalization that directly addresses the chromaticity collapse problem for pure-color scenes. Experiment results show that SAFE consistently improves performance in pure-color scenes. Compared to the best-performing baseline in each metric, it reduces the mean angular error by 10%, the best-25% error by 20%, and the worst-25% error by 5.8%.
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。