SAFE: Scene-Aware Feature Modulation for Color Constancy with Learned Color Space in Pure-Color Scenes

📅 2026-08-14
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This study addresses the ambiguity in color constancy estimation caused by chromatic cue collapse in monochromatic scenes. To overcome this, we propose the SAFE framework coupled with a learnable color space. The method achieves feature modulation and adaptive correction through a four-token structured illumination representation, scene-complexity-adaptive reweighting, and scene-dependent chromatic normalization. Experimental results demonstrate that this approach effectively resolves estimation challenges in monochromatic environments, reducing the mean angular error by 10%, the best 25% error by 20%, and the worst 25% error by 5.8%. These improvements signify a substantial enhancement in both the accuracy and robustness of color constancy estimation under challenging conditions.
📝 Abstract
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%.
Problem

Research questions and friction points this paper is trying to address.

Color Constancy
Pure-Color Scenes
Chromaticity Collapse
Illumination Estimation
Innovation

Methods, ideas, or system contributions that make the work stand out.

Scene-Aware Feature Modulation
Learned Color Space
Color Constancy
Pure-Color Scenes
Chromaticity Collapse
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
Y
Yuan-Kang Lee
MediaTek Inc., Hsinchu, Taiwan
K
Kuan-Lin Chen
National Taiwan University, Taipei, Taiwan
C
Chih-Heng Chang
National Taiwan University, Taipei, Taiwan
J
Jian-Jiun Ding
National Taiwan University, Taipei, Taiwan