Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.09236 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910047362088960 |
|---|---|
| author | Liu, Shuang Yu, Ao Cheng, Linkang Huang, Xiwen Zhao, Li Liu, Junhui Lin, Zhiting Liu, Yu |
| author_facet | Liu, Shuang Yu, Ao Cheng, Linkang Huang, Xiwen Zhao, Li Liu, Junhui Lin, Zhiting Liu, Yu |
| contents | Virtual try-off (VTOFF) aims to recover canonical flat-garment representations from images of dressed persons for standardized display and downstream virtual try-on. Prior methods often treat VTOFF as direct image translation driven by local masks or text-only prompts, overlooking the gap between on-body appearances and flat layouts. This gap frequently leads to inconsistent completion in unobserved regions and unstable garment structure. We propose BridgeDiff, a diffusion-based framework that explicitly bridges human-centric observations and flat-garment synthesis through two complementary components. First, the Garment Condition Bridge Module (GCBM) builds a garment-cue representation that captures global appearance and semantic identity, enabling robust inference of continuous details under partial visibility. Second, the Flat Structure Constraint Module (FSCM) injects explicit flat-garment structural priors via Flat-Constraint Attention (FC-Attention) at selected denoising stages, improving structural stability beyond text-only conditioning. Extensive experiments on standard VTOFF benchmarks show that BridgeDiff achieves state-of-the-art performance, producing higher-quality flat-garment reconstructions while preserving fine-grained appearance and structural integrity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_09236 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | BridgeDiff: Bridging Human Observations and Flat-Garment Synthesis for Virtual Try-Off Liu, Shuang Yu, Ao Cheng, Linkang Huang, Xiwen Zhao, Li Liu, Junhui Lin, Zhiting Liu, Yu Computer Vision and Pattern Recognition Artificial Intelligence Virtual try-off (VTOFF) aims to recover canonical flat-garment representations from images of dressed persons for standardized display and downstream virtual try-on. Prior methods often treat VTOFF as direct image translation driven by local masks or text-only prompts, overlooking the gap between on-body appearances and flat layouts. This gap frequently leads to inconsistent completion in unobserved regions and unstable garment structure. We propose BridgeDiff, a diffusion-based framework that explicitly bridges human-centric observations and flat-garment synthesis through two complementary components. First, the Garment Condition Bridge Module (GCBM) builds a garment-cue representation that captures global appearance and semantic identity, enabling robust inference of continuous details under partial visibility. Second, the Flat Structure Constraint Module (FSCM) injects explicit flat-garment structural priors via Flat-Constraint Attention (FC-Attention) at selected denoising stages, improving structural stability beyond text-only conditioning. Extensive experiments on standard VTOFF benchmarks show that BridgeDiff achieves state-of-the-art performance, producing higher-quality flat-garment reconstructions while preserving fine-grained appearance and structural integrity. |
| title | BridgeDiff: Bridging Human Observations and Flat-Garment Synthesis for Virtual Try-Off |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2603.09236 |