Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2411.00225 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929575010762752 |
|---|---|
| author | Karras, Johanna Li, Yingwei Liu, Nan Zhu, Luyang Yoo, Innfarn Lugmayr, Andreas Lee, Chris Kemelmacher-Shlizerman, Ira |
| author_facet | Karras, Johanna Li, Yingwei Liu, Nan Zhu, Luyang Yoo, Innfarn Lugmayr, Andreas Lee, Chris Kemelmacher-Shlizerman, Ira |
| contents | We present Fashion-VDM, a video diffusion model (VDM) for generating virtual try-on videos. Given an input garment image and person video, our method aims to generate a high-quality try-on video of the person wearing the given garment, while preserving the person's identity and motion. Image-based virtual try-on has shown impressive results; however, existing video virtual try-on (VVT) methods are still lacking garment details and temporal consistency. To address these issues, we propose a diffusion-based architecture for video virtual try-on, split classifier-free guidance for increased control over the conditioning inputs, and a progressive temporal training strategy for single-pass 64-frame, 512px video generation. We also demonstrate the effectiveness of joint image-video training for video try-on, especially when video data is limited. Our qualitative and quantitative experiments show that our approach sets the new state-of-the-art for video virtual try-on. For additional results, visit our project page: https://johannakarras.github.io/Fashion-VDM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_00225 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fashion-VDM: Video Diffusion Model for Virtual Try-On Karras, Johanna Li, Yingwei Liu, Nan Zhu, Luyang Yoo, Innfarn Lugmayr, Andreas Lee, Chris Kemelmacher-Shlizerman, Ira Computer Vision and Pattern Recognition We present Fashion-VDM, a video diffusion model (VDM) for generating virtual try-on videos. Given an input garment image and person video, our method aims to generate a high-quality try-on video of the person wearing the given garment, while preserving the person's identity and motion. Image-based virtual try-on has shown impressive results; however, existing video virtual try-on (VVT) methods are still lacking garment details and temporal consistency. To address these issues, we propose a diffusion-based architecture for video virtual try-on, split classifier-free guidance for increased control over the conditioning inputs, and a progressive temporal training strategy for single-pass 64-frame, 512px video generation. We also demonstrate the effectiveness of joint image-video training for video try-on, especially when video data is limited. Our qualitative and quantitative experiments show that our approach sets the new state-of-the-art for video virtual try-on. For additional results, visit our project page: https://johannakarras.github.io/Fashion-VDM. |
| title | Fashion-VDM: Video Diffusion Model for Virtual Try-On |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.00225 |