Salvato in:
Dettagli Bibliografici
Autori principali: Karras, Johanna, Li, Yingwei, Liu, Nan, Zhu, Luyang, Yoo, Innfarn, Lugmayr, Andreas, Lee, Chris, Kemelmacher-Shlizerman, Ira
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