GCC：基於色彩校準板擴散的生成式色彩恆常性

GCC: Generative Color Constancy via Diffusing a Color Checker

February 24, 2025

作者: Chen-Wei Chang, Cheng-De Fan, Chia-Che Chang, Yi-Chen Lo, Yu-Chee Tseng, Jiun-Long Huang, Yu-Lun Liu

cs.AI

摘要

色彩恒常性方法常因不同相機傳感器的光譜靈敏度差異而難以實現跨設備的泛化。我們提出了GCC，該方法利用擴散模型將色卡修補至圖像中以進行光照估計。我們的核心創新包括：(1) 一種單步確定性推理方法，修補出反映場景光照的色卡；(2) 一種拉普拉斯分解技術，在保持色卡結構的同時允許依賴於光照的色彩適應；(3) 一種基於遮罩的數據增強策略，用於處理不精確的色卡標註。GCC在跨相機場景中展現了卓越的魯棒性，在雙向評估中達到了5.15°和4.32°的頂尖最差25%誤差率。這些結果凸顯了我們方法在不同相機特性下的穩定性和泛化能力，無需針對特定傳感器進行訓練，使其成為現實應用的通用解決方案。

English

Color constancy methods often struggle to generalize across different camera sensors due to varying spectral sensitivities. We present GCC, which leverages diffusion models to inpaint color checkers into images for illumination estimation. Our key innovations include (1) a single-step deterministic inference approach that inpaints color checkers reflecting scene illumination, (2) a Laplacian decomposition technique that preserves checker structure while allowing illumination-dependent color adaptation, and (3) a mask-based data augmentation strategy for handling imprecise color checker annotations. GCC demonstrates superior robustness in cross-camera scenarios, achieving state-of-the-art worst-25% error rates of 5.15{\deg} and 4.32{\deg} in bi-directional evaluations. These results highlight our method's stability and generalization capability across different camera characteristics without requiring sensor-specific training, making it a versatile solution for real-world applications.