发表机构
School of Computer Science and Technology, Beijing Institute of Technology; MT Lab, Meitu Inc.; Gaoling School of Artificial Intelligence, Renmin University of China（北京理工大学计算机科学与技术学院; 美图公司MT实验室; 中国人民大学高瓴人工智能学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究图像重光照问题，提出一致特征传输（CFT）方法，基于整流流通过轨迹级监督联合建模噪声到图像生成及光照一致的源到目标传输，构建数据集实验验证，该方法能改进重光照并推广到其他编辑任务。
AI 中文摘要
图像重光照在保留身份和几何等非光照内容的同时修改光照。现有的基于扩散的方法在复杂光照下往往存在光照变化不稳定或内容保留不一致的问题，因为它们缺乏明确的机制来学习图像之间的特征变换。我们将重光照重新表述为光照特征传输问题，并引入一致特征传输（CFT），这是一种训练原则，可明确强制源图像和目标图像分布之间进行光照一致的传输。基于整流流，CFT通过轨迹级监督联合建模噪声到图像生成和光照一致的源到目标传输。这种双传输公式鼓励隔离特定于光照的变化，同时保留内容对齐的特征。为了支持复杂的光照场景，我们构建了一个具有各种重光照效果的大规模人像重光照数据集。实验表明，与现有的最先进重光照方法相比有持续改进，并证明CFT可以推广到其他编辑任务，包括风格迁移。代码可在指定网址获取。
英文摘要
Image relighting modifies illumination while preserving non-lighting content such as identity and geometry. Existing diffusion-based methods often suffer from unstable illumination changes or inconsistent content preservation under complex lighting, as they lack an explicit mechanism to learn feature transformations between images. We reformulate relighting as an illumination feature transport problem and introduce Consistent Feature Transport (CFT), a training principle that explicitly enforces illumination-consistent transport between source and target image distributions. Built upon rectified flow, CFT jointly models noise-to-image generation and illumination-consistent source-to-target transport through trajectory-level supervision. This dual-transport formulation encourages isolation of illumination-specific variations while preserving content-aligned features. To support complex lighting scenarios, we construct a large-scale portrait relighting dataset with diverse relighting effects. Experiments show consistent improvements over existing state-of-the-art relighting approaches and demonstrate that CFT can generalize to other editing tasks, including style transfer. Code is available at https://github.com/Dixin-Lab/CFT.
