Dressing in the Wild by Watching Dance Videos

by   Xin Dong, et al.

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, therefore, 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, we find that the pixel flow excels at handling loose garments whereas the vertex flow is preferred for hard poses, and by combining their advantages we 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, we 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.


page 1

page 4

page 7

page 8


Towards Scalable Unpaired Virtual Try-On via Patch-Routed Spatially-Adaptive GAN

Image-based virtual try-on is one of the most promising applications of ...

Human Motion Transfer from Poses in the Wild

In this paper, we tackle the problem of human motion transfer, where we ...

PIFu for the Real World: A Self-supervised Framework to Reconstruct Dressed Human from Single-view Images

It is very challenging to accurately reconstruct sophisticated human geo...

Disentangled Cycle Consistency for Highly-realistic Virtual Try-On

Image virtual try-on replaces the clothes on a person image with a desir...

3D Clothed Human Reconstruction in the Wild

Although much progress has been made in 3D clothed human reconstruction,...

GP-VTON: Towards General Purpose Virtual Try-on via Collaborative Local-Flow Global-Parsing Learning

Image-based Virtual Try-ON aims to transfer an in-shop garment onto a sp...

Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events

Along with the development of the modern smart city, human-centric video...

Please sign up or login with your details

Forgot password? Click here to reset