IntrinsicEdit: Precise generative image manipulation in intrinsic space
Abstract
Generative diffusion models have advanced image editing by delivering high-quality results through intuitive interfaces such as prompts, scribbles, and semantic drawing. However, these interfaces lack precise control, and associated editing methods often specialize in a single task. We introduce a versatile workflow for a range of editing tasks which operates in an intrinsic-image latent space, enabling semantic, local manipulation with pixel precision while automatically handling effects like reflections and shadows. We build on the RGB↔X diffusion framework and address its key deficiencies: the lack of identity preservation and the need to update multiple channels to achieve plausible results. We propose an edit-friendly diffusion inversion and prompt-embedding optimization to enable precise and efficient editing of only the relevant channels. Our method achieves identity preservation and resolves global illumination, without requiring task-specific model fine-tuning. We demonstrate state-of-the-art performance across a variety of tasks on complex images, including material adjustments, object insertion and removal, global relighting, and their combinations.
Downloads and links
- paper (PDF, 11 MB)
- supplemental document (PDF, 25 MB)
- Arxiv preprint
- project page
- citation (BIB)
BibTeX reference
@article{Lyu:2025:IntrinsicEdit, author = {Linjie Lyu and Valentin Deschaintre and Yannick Hold-Geoffroy and Miloš Hašan and Jae Shin Yoon and Thomas Leimkühler and Christian Theobalt and Iliyan Georgiev}, title = {IntrinsicEdit: Precise generative image manipulation in intrinsic space}, journal = {ACM Transactions on Graphics (Proceedings of SIGGRAPH)}, year = {2025}, volume = {44}, number = {4}, doi = {10.1145/3731173} }