OmniVTON++: Training-Free Universal Virtual Try-On with Principal Pose Guidance
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908878856257536 |
|---|---|
| author | Yang, Zhaotong Du, Yong He, Shengfeng Li, Yuhui Li, Xinzhe Xu, Yangyang Dong, Junyu Yang, Jian |
| author_facet | Yang, Zhaotong Du, Yong He, Shengfeng Li, Yuhui Li, Xinzhe Xu, Yangyang Dong, Junyu Yang, Jian |
| contents | Image-based Virtual Try-On (VTON) concerns the synthesis of realistic person imagery through garment re-rendering under human pose and body constraints. In practice, however, existing approaches are typically optimized for specific data conditions, making their deployment reliant on retraining and limiting their generalization as a unified solution. We present OmniVTON++, a training-free VTON framework designed for universal applicability. It addresses the intertwined challenges of garment alignment, human structural coherence, and boundary continuity by coordinating Structured Garment Morphing for correspondence-driven garment adaptation, Principal Pose Guidance for step-wise structural regulation during diffusion sampling, and Continuous Boundary Stitching for boundary-aware refinement, forming a cohesive pipeline without task-specific retraining. Experimental results demonstrate that OmniVTON++ achieves state-of-the-art performance across diverse generalization settings, including cross-dataset and cross-garment-type evaluations, while reliably operating across scenarios and diffusion backbones within a single formulation. In addition to single-garment, single-human cases, the framework supports multi-garment, multi-human, and anime character virtual try-on, expanding the scope of virtual try-on applications. The code is available at https://github.com/Jerome-Young/OmniVTON-PlusPlus. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_14552 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | OmniVTON++: Training-Free Universal Virtual Try-On with Principal Pose Guidance Yang, Zhaotong Du, Yong He, Shengfeng Li, Yuhui Li, Xinzhe Xu, Yangyang Dong, Junyu Yang, Jian Computer Vision and Pattern Recognition Image-based Virtual Try-On (VTON) concerns the synthesis of realistic person imagery through garment re-rendering under human pose and body constraints. In practice, however, existing approaches are typically optimized for specific data conditions, making their deployment reliant on retraining and limiting their generalization as a unified solution. We present OmniVTON++, a training-free VTON framework designed for universal applicability. It addresses the intertwined challenges of garment alignment, human structural coherence, and boundary continuity by coordinating Structured Garment Morphing for correspondence-driven garment adaptation, Principal Pose Guidance for step-wise structural regulation during diffusion sampling, and Continuous Boundary Stitching for boundary-aware refinement, forming a cohesive pipeline without task-specific retraining. Experimental results demonstrate that OmniVTON++ achieves state-of-the-art performance across diverse generalization settings, including cross-dataset and cross-garment-type evaluations, while reliably operating across scenarios and diffusion backbones within a single formulation. In addition to single-garment, single-human cases, the framework supports multi-garment, multi-human, and anime character virtual try-on, expanding the scope of virtual try-on applications. The code is available at https://github.com/Jerome-Young/OmniVTON-PlusPlus. |
| title | OmniVTON++: Training-Free Universal Virtual Try-On with Principal Pose Guidance |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.14552 |