Saved in:
Bibliographic Details
Main Authors: Naik, Shanthika, Singh, Kunwar, Srivastava, Astitva, Sirikonda, Dhawal, Raj, Amit, Jampani, Varun, Sharma, Avinash
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.03108
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911749382340608
author Naik, Shanthika
Singh, Kunwar
Srivastava, Astitva
Sirikonda, Dhawal
Raj, Amit
Jampani, Varun
Sharma, Avinash
author_facet Naik, Shanthika
Singh, Kunwar
Srivastava, Astitva
Sirikonda, Dhawal
Raj, Amit
Jampani, Varun
Sharma, Avinash
contents We propose a novel self-supervised framework for retargeting non-parameterized 3D garments onto 3D human avatars of arbitrary shapes and poses, enabling 3D virtual try-on (VTON). Existing self-supervised 3D retargeting methods only support parametric and canonical garments, which can only be draped over parametric body, e.g. SMPL. To facilitate the non-parametric garments and body, we propose a novel method that introduces Isomap Embedding based correspondences matching between the garment and the human body to get a coarse alignment between the two meshes. We perform neural refinement of the coarse alignment in a self-supervised setting. Further, we leverage a Laplacian detail integration method for preserving the inherent details of the input garment. For evaluating our 3D non-parametric garment retargeting framework, we propose a dataset of 255 real-world garments with realistic noise and topological deformations. The dataset contains $44$ unique garments worn by 15 different subjects in 5 distinctive poses, captured using a multi-view RGBD capture setup. We show superior retargeting quality on non-parametric garments and human avatars over existing state-of-the-art methods, acting as the first-ever baseline on the proposed dataset for non-parametric 3D garment retargeting.
format Preprint
id arxiv_https___arxiv_org_abs_2401_03108
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Dress-Me-Up: A Dataset & Method for Self-Supervised 3D Garment Retargeting
Naik, Shanthika
Singh, Kunwar
Srivastava, Astitva
Sirikonda, Dhawal
Raj, Amit
Jampani, Varun
Sharma, Avinash
Computer Vision and Pattern Recognition
We propose a novel self-supervised framework for retargeting non-parameterized 3D garments onto 3D human avatars of arbitrary shapes and poses, enabling 3D virtual try-on (VTON). Existing self-supervised 3D retargeting methods only support parametric and canonical garments, which can only be draped over parametric body, e.g. SMPL. To facilitate the non-parametric garments and body, we propose a novel method that introduces Isomap Embedding based correspondences matching between the garment and the human body to get a coarse alignment between the two meshes. We perform neural refinement of the coarse alignment in a self-supervised setting. Further, we leverage a Laplacian detail integration method for preserving the inherent details of the input garment. For evaluating our 3D non-parametric garment retargeting framework, we propose a dataset of 255 real-world garments with realistic noise and topological deformations. The dataset contains $44$ unique garments worn by 15 different subjects in 5 distinctive poses, captured using a multi-view RGBD capture setup. We show superior retargeting quality on non-parametric garments and human avatars over existing state-of-the-art methods, acting as the first-ever baseline on the proposed dataset for non-parametric 3D garment retargeting.
title Dress-Me-Up: A Dataset & Method for Self-Supervised 3D Garment Retargeting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.03108