Consistent Feature Transport for Image Relighting

2026-07-20

AI Summary

This work addresses the challenge of maintaining identity and geometric consistency under extreme illumination changes in image relighting. To this end, it formulates relighting as an illumination feature transfer problem and introduces a Consistent Feature Transfer (CFT) training framework. CFT jointly models noise-to-image generation and source-to-target illumination transfer via rectified flows and incorporates trajectory-level supervision to explicitly disentangle illumination and content features. The authors also construct the first large-scale portrait dataset featuring complex lighting conditions. Experimental results demonstrate that the proposed method significantly outperforms existing approaches in both relighting quality and content fidelity, and further generalizes effectively to other editing tasks such as style transfer.

Abstract

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.

Problem

• image relighting
• content preservation
• illumination consistency
• feature transformation
• complex lighting

Innovation

• Consistent Feature Transport
• rectified flow
• illumination feature transport
• trajectory-level supervision
• image relighting