IntrinsicEdit: Precise generative image manipulation in intrinsic space
ACM Transactions on Graphics · 01.08.2025 · 44 (4) · 1-13
DOI: 10.1145/3731173 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 27.07.2025. Verfasst von Linjie Lyu und 7 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 88 Literaturangaben.
Abstract (Originalsprache)
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.
Zitieren
APA
Lyu, L., Deschaintre, V., Hold-Geoffroy, Y., Hašan, M., Yoon, J. S., Leimkühler, T., Theobalt, C., & Georgiev, I. (2025). IntrinsicEdit: Precise generative image manipulation in intrinsic space. ACM Transactions on Graphics, 44(4), 1-13. https://doi.org/10.1145/3731173
Vancouver
Lyu L, Deschaintre V, Hold-Geoffroy Y, Hašan M, Yoon JS, Leimkühler T, et al. IntrinsicEdit: Precise generative image manipulation in intrinsic space. ACM Transactions on Graphics. 2025;44(4):1-13. doi:10.1145/3731173
BibTeX
@article{Lyu2025,
author = {Lyu, Linjie and Deschaintre, Valentin and Hold-Geoffroy, Yannick and Hašan, Miloš and Yoon, Jae Shin and Leimkühler, Thomas and Theobalt, Christian and Georgiev, Iliyan},
title = {IntrinsicEdit: Precise generative image manipulation in intrinsic space},
journal = {ACM Transactions on Graphics},
year = {2025},
volume = {44},
number = {4},
pages = {1--13},
doi = {10.1145/3731173}
}
EUVIMED