GCC: Generative Color Constancy via Diffusing a Color Checker
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917967662415872 |
|---|---|
| author | Chang, Chen-Wei Fan, Cheng-De Chang, Chia-Che Lo, Yi-Chen Tseng, Yu-Chee Huang, Jiun-Long Liu, Yu-Lun |
| author_facet | Chang, Chen-Wei Fan, Cheng-De Chang, Chia-Che Lo, Yi-Chen Tseng, Yu-Chee Huang, Jiun-Long Liu, Yu-Lun |
| contents | 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. By harnessing rich priors from pre-trained diffusion models, GCC demonstrates strong robustness in challenging cross-camera scenarios. These results highlight our method's effective generalization capability across different camera characteristics without requiring sensor-specific training, making it a versatile and practical solution for real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_17435 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GCC: Generative Color Constancy via Diffusing a Color Checker Chang, Chen-Wei Fan, Cheng-De Chang, Chia-Che Lo, Yi-Chen Tseng, Yu-Chee Huang, Jiun-Long Liu, Yu-Lun Computer Vision and Pattern Recognition 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. By harnessing rich priors from pre-trained diffusion models, GCC demonstrates strong robustness in challenging cross-camera scenarios. These results highlight our method's effective generalization capability across different camera characteristics without requiring sensor-specific training, making it a versatile and practical solution for real-world applications. |
| title | GCC: Generative Color Constancy via Diffusing a Color Checker |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.17435 |