Salvato in:
Dettagli Bibliografici
Autori principali: Zuo, Tongchun, Huang, Zaiyu, Ning, Shuliang, Lin, Ente, Liang, Chao, Zheng, Zerong, Jiang, Jianwen, Zhang, Yuan, Gao, Mingyuan, Dong, Xin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2508.02807
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916880666591232
author Zuo, Tongchun
Huang, Zaiyu
Ning, Shuliang
Lin, Ente
Liang, Chao
Zheng, Zerong
Jiang, Jianwen
Zhang, Yuan
Gao, Mingyuan
Dong, Xin
author_facet Zuo, Tongchun
Huang, Zaiyu
Ning, Shuliang
Lin, Ente
Liang, Chao
Zheng, Zerong
Jiang, Jianwen
Zhang, Yuan
Gao, Mingyuan
Dong, Xin
contents Video virtual try-on (VVT) technology has garnered considerable academic interest owing to its promising applications in e-commerce advertising and entertainment. However, most existing end-to-end methods rely heavily on scarce paired garment-centric datasets and fail to effectively leverage priors of advanced visual models and test-time inputs, making it challenging to accurately preserve fine-grained garment details and maintain temporal consistency in unconstrained scenarios. To address these challenges, we propose DreamVVT, a carefully designed two-stage framework built upon Diffusion Transformers (DiTs), which is inherently capable of leveraging diverse unpaired human-centric data to enhance adaptability in real-world scenarios. To further leverage prior knowledge from pretrained models and test-time inputs, in the first stage, we sample representative frames from the input video and utilize a multi-frame try-on model integrated with a vision-language model (VLM), to synthesize high-fidelity and semantically consistent keyframe try-on images. These images serve as complementary appearance guidance for subsequent video generation. \textbf{In the second stage}, skeleton maps together with fine-grained motion and appearance descriptions are extracted from the input content, and these along with the keyframe try-on images are then fed into a pretrained video generation model enhanced with LoRA adapters. This ensures long-term temporal coherence for unseen regions and enables highly plausible dynamic motions. Extensive quantitative and qualitative experiments demonstrate that DreamVVT surpasses existing methods in preserving detailed garment content and temporal stability in real-world scenarios. Our project page https://virtu-lab.github.io/
format Preprint
id arxiv_https___arxiv_org_abs_2508_02807
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework
Zuo, Tongchun
Huang, Zaiyu
Ning, Shuliang
Lin, Ente
Liang, Chao
Zheng, Zerong
Jiang, Jianwen
Zhang, Yuan
Gao, Mingyuan
Dong, Xin
Computer Vision and Pattern Recognition
Video virtual try-on (VVT) technology has garnered considerable academic interest owing to its promising applications in e-commerce advertising and entertainment. However, most existing end-to-end methods rely heavily on scarce paired garment-centric datasets and fail to effectively leverage priors of advanced visual models and test-time inputs, making it challenging to accurately preserve fine-grained garment details and maintain temporal consistency in unconstrained scenarios. To address these challenges, we propose DreamVVT, a carefully designed two-stage framework built upon Diffusion Transformers (DiTs), which is inherently capable of leveraging diverse unpaired human-centric data to enhance adaptability in real-world scenarios. To further leverage prior knowledge from pretrained models and test-time inputs, in the first stage, we sample representative frames from the input video and utilize a multi-frame try-on model integrated with a vision-language model (VLM), to synthesize high-fidelity and semantically consistent keyframe try-on images. These images serve as complementary appearance guidance for subsequent video generation. \textbf{In the second stage}, skeleton maps together with fine-grained motion and appearance descriptions are extracted from the input content, and these along with the keyframe try-on images are then fed into a pretrained video generation model enhanced with LoRA adapters. This ensures long-term temporal coherence for unseen regions and enables highly plausible dynamic motions. Extensive quantitative and qualitative experiments demonstrate that DreamVVT surpasses existing methods in preserving detailed garment content and temporal stability in real-world scenarios. Our project page https://virtu-lab.github.io/
title DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.02807