Dressing in the Wild

Virtual try-on (garment transfer) in varied poses from a new dataset of dancing videos

Released in: Dressing in the Wild by Watching Dance Videos



While significant progress has been made in garment transfer, one of the most applicable directions of human-centric image generation, existing works overlook the in-the-wild imagery, presenting severe garment-person misalignment as well as noticeable degradation in fine texture details. This paper attends to virtual try-on in real-world scenes and brings essential improvements in authenticity and naturalness especially for loose garment (e.g., skirts, formal dresses), challenging poses (e.g., cross arms, bent legs), and cluttered backgrounds. Specifically, the authors find that the pixel flow excels at handling loose garments whereas the vertex flow is preferred for hard poses, and by combining their advantages they propose a novel generative network called wFlow that can effectively push up garment transfer to in-the-wild context. Moreover, former approaches require paired images for training. Instead, the authors cut down the laboriousness by working on a newly constructed large-scale video dataset named Dance50k with self-supervised cross-frame training and an online cycle optimization. The proposed Dance50k can boost real-world virtual dressing by covering a wide variety of garments under dancing poses. Extensive experiments demonstrate the superiority of our wFlow in generating realistic garment transfer results for in-the-wild images without resorting to expensive paired datasets.


Year Released

Key Links & Stats

Dressing in the Wild by Watching Dance Videos

@InProceedings{dong2022wflow, title={Dressing in the Wild by Watching Dance Videos}, author={Xin Dong and Fuwei Zhao and Zhenyu Xie and Xijin Zhang and Kang Du and Min Zheng and Xiang Long and Xiaodan Liang and Jianchao Yang1}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year={2022} }

ML Tasks

  1. Image Generation

ML Platform

  1. Not Applicable


  1. Still Image


  1. Digital Human

CG Platform

  1. Not Applicable

Related organizations


Sun Yat-sen University