GenColor: Generative and Expressive Color Enhancement with Pixel-Perfect Texture Preservation

Generative methods ( e.g ., Midjourney), on the other hand, create dramatic transformations but alter textures, compromising authenticity. The difference maps ( 2 nd row) show GenColor making selective region-specific adjustments similar to Midjourney, but with better results than Expert C (the best retoucher in Adobe5K [2]), which is limited to global filter adjustments. Abstract Color enhancement is a crucial yet challenging task in digital photography. It demands methods that are (i) expressive enough for fine-grained adjustments, (ii) adaptable to diverse inputs, and (iii) able to preserve texture. Existing approaches typically fall short in at least one of these aspects, yielding unsatisfactory re-sults. We propose GenColor, a novel diffusion-based framework for sophisticated, texture-preserving color enhancement. GenColor reframes the task as conditional image generation. Leveraging ControlNet and a tailored training scheme, it learns advanced color transformations that adapt to diverse lighting and content. We train GenColor on ARTISAN, our newly collected large-scale