CanonCGT: Reference-Based Color Grading via Canonical Pivot Representation
This work addresses unstable tone mappings in reference-based color grading for image editing applications, offering a more robust solution.
CanonCGT introduces a two-stage framework using a canonical pivot representation for reference-based color grading, achieving photorealistic and tonally consistent results that surpass state-of-the-art methods in stability and visual fidelity.
Reference-based color grading aims to reproduce the tonal mood and lighting of a reference while preserving color harmony and scene structure. Existing photorealistic and filter-based methods often produce unstable tone mappings -- over-shifting or inconsistently retaining colors -- leading to unnatural results. We propose CanonCGT, a two-stage framework built on a canonical pivot -- a style-neutral intermediate representation for stable color mapping. The first stage canonicalizes the input by removing intrinsic tonal bias, and the second color-grades it to match the reference style. A dual-phase training scheme, DP-CGT, combines supervised preset learning with self-supervised refinement on unpaired photographs. CanonCGT delivers photorealistic and tonally consistent results across diverse datasets, surpassing state-of-the-art methods in stability and visual fidelity. Our codes are available at \href{https://github.com/Jinwon-Ko/CanonCGT}{https://github.com/Jinwon-Ko/CanonCGT}