ViViD: Video Virtual Try-on using Diffusion Models

1USTC 2Alibaba Group

Video Try-on



Pipeline

Pipeline.

Abstract

Video virtual try-on aims to transfer a clothing item onto the video of a target person. Directly applying the technique of image-based try-on to the video domain in a frame-wise manner will cause temporal-inconsistent outcomes while previous video-based try-on solutions can only generate low visual quality and blurring results. In this work, we present ViViD, a novel framework employing powerful diffusion models to tackle the task of video virtual try-on. Specifically, we design the Garment Encoder to extract fine-grained clothing semantic features, guiding the model to capture garment details and inject them into the target video through the proposed attention feature fusion mechanism. To ensure spatial-temporal consistency, we introduce a lightweight Pose Encoder to encode pose signals, enabling the model to learn the interactions between clothing and human posture and insert hierarchical Temporal Modules into the text-to-image stable diffusion model for more coherent and lifelike video synthesis. Furthermore, we collect a new dataset, which is the largest, with the most diverse types of garments and the highest resolution for the task of video virtual try-on to date. Extensive experiments demonstrate that our approach is able to yield satisfactory video try-on results. The dataset, codes, and weights will be publicly available.

More Results

BibTeX

@misc{fang2024vivid,
        title={ViViD: Video Virtual Try-on using Diffusion Models}, 
        author={Zixun Fang and Wei Zhai and Aimin Su and Hongliang Song and Kai Zhu and Mao Wang and Yu Chen and Zhiheng Liu and Yang Cao and Zheng-Jun Zha},
        year={2024},
        eprint={2405.11794},
        archivePrefix={arXiv},
        primaryClass={cs.CV}
  }