Virtual Try-On for Cultural Clothing: A Benchmarking Study
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911495911112704 |
|---|---|
| author | Islam, Muhammad Tausif Ul Awlad, Shahir Adib, Sameen Yeaser Rahman, Md. Atiqur Ahmed, Sabbir Kabir, Md. Hasanul |
| author_facet | Islam, Muhammad Tausif Ul Awlad, Shahir Adib, Sameen Yeaser Rahman, Md. Atiqur Ahmed, Sabbir Kabir, Md. Hasanul |
| contents | Although existing virtual try-on systems have made significant progress with the advent of diffusion models, the current benchmarks of these models are based on datasets that are dominant in western-style clothing and female models, limiting their ability to generalize culturally diverse clothing styles. In this work, we introduce BD-VITON, a virtual try-on dataset focused on Bangladeshi garments, including saree, panjabi and salwar kameez, covering both male and female categories as well. These garments present unique structural challenges such as complex draping, asymmetric layering, and high deformation complexities which are underrepresented in the original VITON dataset. To establish strong baselines, we retrain and evaluate try-on models, namely StableViton, HR-VITON, and VITON-HD on our dataset. Our experiments demonstrate consistent improvements in terms of both quantitative and qualitative analysis, compared to zero shot inference. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07291 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Virtual Try-On for Cultural Clothing: A Benchmarking Study Islam, Muhammad Tausif Ul Awlad, Shahir Adib, Sameen Yeaser Rahman, Md. Atiqur Ahmed, Sabbir Kabir, Md. Hasanul Computer Vision and Pattern Recognition Although existing virtual try-on systems have made significant progress with the advent of diffusion models, the current benchmarks of these models are based on datasets that are dominant in western-style clothing and female models, limiting their ability to generalize culturally diverse clothing styles. In this work, we introduce BD-VITON, a virtual try-on dataset focused on Bangladeshi garments, including saree, panjabi and salwar kameez, covering both male and female categories as well. These garments present unique structural challenges such as complex draping, asymmetric layering, and high deformation complexities which are underrepresented in the original VITON dataset. To establish strong baselines, we retrain and evaluate try-on models, namely StableViton, HR-VITON, and VITON-HD on our dataset. Our experiments demonstrate consistent improvements in terms of both quantitative and qualitative analysis, compared to zero shot inference. |
| title | Virtual Try-On for Cultural Clothing: A Benchmarking Study |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.07291 |