Undress to Redress: A Training-Free Framework for Virtual Try-On
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909731911630848 |
|---|---|
| author | Li, Zhiying Wu, Junhao Jin, Yeying Gao, Daiheng Ji, Yun Kong, Kaichuan Yu, Lei Xu, Hao Chen, Kai Gu, Bruce Wang, Nana Fan, Zhaoxin |
| author_facet | Li, Zhiying Wu, Junhao Jin, Yeying Gao, Daiheng Ji, Yun Kong, Kaichuan Yu, Lei Xu, Hao Chen, Kai Gu, Bruce Wang, Nana Fan, Zhaoxin |
| contents | Virtual try-on (VTON) is a crucial task for enhancing user experience in online shopping by generating realistic garment previews on personal photos. Although existing methods have achieved impressive results, they struggle with long-sleeve-to-short-sleeve conversions-a common and practical scenario-often producing unrealistic outputs when exposed skin is underrepresented in the original image. We argue that this challenge arises from the ''majority'' completion rule in current VTON models, which leads to inaccurate skin restoration in such cases. To address this, we propose UR-VTON (Undress-Redress Virtual Try-ON), a novel, training-free framework that can be seamlessly integrated with any existing VTON method. UR-VTON introduces an ''undress-to-redress'' mechanism: it first reveals the user's torso by virtually ''undressing,'' then applies the target short-sleeve garment, effectively decomposing the conversion into two more manageable steps. Additionally, we incorporate Dynamic Classifier-Free Guidance scheduling to balance diversity and image quality during DDPM sampling, and employ Structural Refiner to enhance detail fidelity using high-frequency cues. Finally, we present LS-TON, a new benchmark for long-sleeve-to-short-sleeve try-on. Extensive experiments demonstrate that UR-VTON outperforms state-of-the-art methods in both detail preservation and image quality. Code will be released upon acceptance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_07680 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Undress to Redress: A Training-Free Framework for Virtual Try-On Li, Zhiying Wu, Junhao Jin, Yeying Gao, Daiheng Ji, Yun Kong, Kaichuan Yu, Lei Xu, Hao Chen, Kai Gu, Bruce Wang, Nana Fan, Zhaoxin Computer Vision and Pattern Recognition Virtual try-on (VTON) is a crucial task for enhancing user experience in online shopping by generating realistic garment previews on personal photos. Although existing methods have achieved impressive results, they struggle with long-sleeve-to-short-sleeve conversions-a common and practical scenario-often producing unrealistic outputs when exposed skin is underrepresented in the original image. We argue that this challenge arises from the ''majority'' completion rule in current VTON models, which leads to inaccurate skin restoration in such cases. To address this, we propose UR-VTON (Undress-Redress Virtual Try-ON), a novel, training-free framework that can be seamlessly integrated with any existing VTON method. UR-VTON introduces an ''undress-to-redress'' mechanism: it first reveals the user's torso by virtually ''undressing,'' then applies the target short-sleeve garment, effectively decomposing the conversion into two more manageable steps. Additionally, we incorporate Dynamic Classifier-Free Guidance scheduling to balance diversity and image quality during DDPM sampling, and employ Structural Refiner to enhance detail fidelity using high-frequency cues. Finally, we present LS-TON, a new benchmark for long-sleeve-to-short-sleeve try-on. Extensive experiments demonstrate that UR-VTON outperforms state-of-the-art methods in both detail preservation and image quality. Code will be released upon acceptance. |
| title | Undress to Redress: A Training-Free Framework for Virtual Try-On |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.07680 |