OOTDiffusion: Outfitting Fusion Based Latent Diffusion for Controllable Virtual Try-On
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (9) · 8996-9004
DOI: 10.1609/aaai.v39i9.32973 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Yuhao Xu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 116-mal zitiert (Crossref).
Abstract (Originalsprache)
We present OOTDiffusion, a novel network architecture for realistic and controllable image-based virtual try-on (VTON). We leverage the power of pretrained latent diffusion models, designing an outfitting UNet to learn the detailed garment features. Without a redundant warping process, the garment features are precisely aligned with the target human body via the proposed outfitting fusion in the self-attention layers of the denoising UNet. In order to further enhance the controllability, we introduce outfitting dropout to the training process, which enables us to adjust the strength of the garment features through classifier-free guidance. Our comprehensive experiments on the VITON-HD and Dress Code datasets demonstrate that OOTDiffusion efficiently generates high-quality try-on results for arbitrary human and garment images, which outperforms other VTON methods in both realism and controllability, indicating a breakthrough in virtual try-on.
Zitieren
APA
Xu, Y., Gu, T., Chen, W., & Chen, A. (2025). OOTDiffusion: Outfitting Fusion Based Latent Diffusion for Controllable Virtual Try-On. Proceedings of the AAAI Conference on Artificial Intelligence, 39(9), 8996-9004. https://doi.org/10.1609/aaai.v39i9.32973
Vancouver
Xu Y, Gu T, Chen W, Chen A. OOTDiffusion: Outfitting Fusion Based Latent Diffusion for Controllable Virtual Try-On. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(9):8996-9004. doi:10.1609/aaai.v39i9.32973
BibTeX
@article{Xu2025,
author = {Xu, Yuhao and Gu, Tao and Chen, Weifeng and Chen, Arlene},
title = {OOTDiffusion: Outfitting Fusion Based Latent Diffusion for Controllable Virtual Try-On},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {9},
pages = {8996--9004},
doi = {10.1609/aaai.v39i9.32973}
}
EUVIMED