๐ธ GCC: Generative Color Constancy via Diffusing a Color Checker
๐ GitHub Repository | ๐ Project Page | ๐ Paper
Upload a RAW image to automatically correct its white balance using our diffusion-based color constancy method. GCC generates a color checker that accurately reflects the scene's ambient lighting, then uses it to estimate the illuminant and apply precise white balance correction.
Getting Started:
- Upload Your Image: Use the image upload box on the left to provide your RAW image (supports various bit depths).
- Process: Click the "๐ Process Image" button to start the color constancy correction.
- View Results: The generated color checker and white balanced result will appear below.
- Download: Right-click on any result image to save it as PNG to your device.
- Technical Details (Optional): After processing, you can view detailed processing information in the expandable section below.
๐ค Input Image
๐ฏ Generated Color Checker (512ร512)
โ๏ธ White Balanced Result
Processing Steps:
- Preprocessing: Resize input to 512ร512, apply gamma correction (ฮณ=2.2)
- Color Checker Generation: Generate scene-harmonized color checker at image center using diffusion model
- Illuminant Estimation: Extract illuminant from gray patch (patch 20)
- White Balance Correction: Apply RGB gains in linear space, then apply gamma correction (ฮณ=2.2) for sRGB output
๐ Citation
@InProceedings{Chang_2025_CVPR,
author = {Chang, Chen-Wei and Fan, Cheng-De and Chang, Chia-Che and Lo, Yi-Chen and Tseng, Yu-Chee and Huang, Jiun-Long and Liu, Yu-Lun},
title = {GCC: Generative Color Constancy via Diffusing a Color Checker},
booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR)},
month = {June},
year = {2025},
pages = {10868-10878}
}