Saved in:
Bibliographic Details
Main Authors: Dong, Junting, Fang, Qi, Huang, Zehuan, Xu, Xudong, Wang, Jingbo, Peng, Sida, Dai, Bo
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.16748
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914770574114816
author Dong, Junting
Fang, Qi
Huang, Zehuan
Xu, Xudong
Wang, Jingbo
Peng, Sida
Dai, Bo
author_facet Dong, Junting
Fang, Qi
Huang, Zehuan
Xu, Xudong
Wang, Jingbo
Peng, Sida
Dai, Bo
contents This paper addresses the task of 3D clothed human generation from textural descriptions. Previous works usually encode the human body and clothes as a holistic model and generate the whole model in a single-stage optimization, which makes them struggle for clothing editing and meanwhile lose fine-grained control over the whole generation process. To solve this, we propose a layer-wise clothed human representation combined with a progressive optimization strategy, which produces clothing-disentangled 3D human models while providing control capacity for the generation process. The basic idea is progressively generating a minimal-clothed human body and layer-wise clothes. During clothing generation, a novel stratified compositional rendering method is proposed to fuse multi-layer human models, and a new loss function is utilized to help decouple the clothing model from the human body. The proposed method achieves high-quality disentanglement, which thereby provides an effective way for 3D garment generation. Extensive experiments demonstrate that our approach achieves state-of-the-art 3D clothed human generation while also supporting cloth editing applications such as virtual try-on. Project page: http://jtdong.com/tela_layer/
format Preprint
id arxiv_https___arxiv_org_abs_2404_16748
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TELA: Text to Layer-wise 3D Clothed Human Generation
Dong, Junting
Fang, Qi
Huang, Zehuan
Xu, Xudong
Wang, Jingbo
Peng, Sida
Dai, Bo
Computer Vision and Pattern Recognition
This paper addresses the task of 3D clothed human generation from textural descriptions. Previous works usually encode the human body and clothes as a holistic model and generate the whole model in a single-stage optimization, which makes them struggle for clothing editing and meanwhile lose fine-grained control over the whole generation process. To solve this, we propose a layer-wise clothed human representation combined with a progressive optimization strategy, which produces clothing-disentangled 3D human models while providing control capacity for the generation process. The basic idea is progressively generating a minimal-clothed human body and layer-wise clothes. During clothing generation, a novel stratified compositional rendering method is proposed to fuse multi-layer human models, and a new loss function is utilized to help decouple the clothing model from the human body. The proposed method achieves high-quality disentanglement, which thereby provides an effective way for 3D garment generation. Extensive experiments demonstrate that our approach achieves state-of-the-art 3D clothed human generation while also supporting cloth editing applications such as virtual try-on. Project page: http://jtdong.com/tela_layer/
title TELA: Text to Layer-wise 3D Clothed Human Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.16748