High-quality 3D Clothing Reconstruction and Virtual-Try-On: Pants case

Thai Thanh Tuan, Youngsik Yun, Heejune Ahn

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Virtual try-on (VTON) is filling the gap between online and offline shopping. This paper extends Cloth3D, which uses top clothing only, and proposes a pipeline for high-resolution virtual try-on for pants based on 3D clothing reconstruction. In-shop pants image is first reconstructed into 3D by finding the SMPL body model fitted to the pants and building the clothing model. Then, the clothing model is reposed to the human reference image and projected to a 2D image to get 3D warped pants. These warped pants and the identities from the reference person image are going through the blending network to get the try-on. Moreover, a target segmentation is also estimated for control input for the blending (in-painting) network. Our experiments and evaluation on a new fashion dataset show natural VTON results for service.

Original languageEnglish
Title of host publication2022 International Conference on Multimedia Analysis and Pattern Recognition, MAPR 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665474108
DOIs
StatePublished - 2022
Event2022 International Conference on Multimedia Analysis and Pattern Recognition, MAPR 2022 - Phu Quoc Island, Viet Nam
Duration: 13 Oct 202214 Oct 2022

Publication series

Name2022 International Conference on Multimedia Analysis and Pattern Recognition, MAPR 2022 - Proceedings

Conference

Conference2022 International Conference on Multimedia Analysis and Pattern Recognition, MAPR 2022
Country/TerritoryViet Nam
CityPhu Quoc Island
Period13/10/2214/10/22

Keywords

  • 3D clothing reconstruction
  • Depth estimation
  • In-painting
  • VTON(Virtual try-on)
  • conditional Image generation

Fingerprint

Dive into the research topics of 'High-quality 3D Clothing Reconstruction and Virtual-Try-On: Pants case'. Together they form a unique fingerprint.

Cite this