OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911790757052416 |
|---|---|
| author | Xu, Yuhao Gu, Tao Chen, Weifeng Chen, Chengcai |
| author_facet | Xu, Yuhao Gu, Tao Chen, Weifeng Chen, Chengcai |
| contents | 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 garment detail 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 an impressive breakthrough in virtual try-on. Our source code is available at https://github.com/levihsu/OOTDiffusion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_01779 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on Xu, Yuhao Gu, Tao Chen, Weifeng Chen, Chengcai Computer Vision and Pattern Recognition 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 garment detail 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 an impressive breakthrough in virtual try-on. Our source code is available at https://github.com/levihsu/OOTDiffusion. |
| title | OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.01779 |