CanonCGT：基于规范枢轴表示的参考图引导色彩分级
CanonCGT: Reference-Based Color Grading via Canonical Pivot Representation
用「风格中立的规范枢轴」作为中间表示，把色调迁移拆成去偏规范化与参考匹配两步，可缓解参考图引导编辑中色调映射不稳定、颜色过冲的问题，这一中间表示思路可迁移到其他参考引导的图像到图像任务。
原文依据 a canonical pivot --- a style-neutral intermediate representation for stable color mapping
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论参考图引导的色彩分级旨在复现参考图的色调氛围与光照，同时保持色彩和谐与场景结构。现有的照片级真实感方法与基于滤镜的方法往往产生不稳定的色调映射——或过度偏移，或不一致地保留颜色——从而导致不自然的结果。我们提出 CanonCGT，一个建立在规范枢轴之上的两阶段框架，该枢轴是一种风格中立的中间表示，用于实现稳定的色彩映射。第一阶段通过去除输入固有的色调偏置对其进行规范化，第二阶段再对其进行色彩分级以匹配参考风格。双阶段训练方案 DP-CGT 将有监督的预设学习与在非配对照片上的自监督精调相结合。CanonCGT 在多种数据集上给出照片级真实感且色调一致的结果，在稳定性与视觉保真度上超越最优方法。我们的代码已公开于 \href https://github.com/Jinwon-Ko/CanonCGT https://github.com/Jinwon-Ko/CanonCGT 。
英文原文摘要 995 字符
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 .