Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Jionghao, Liu, Yuan, Dou, Zhiyang, Yu, Zhengming, Liang, Yongqing, Lin, Cheng, Li, Xin, Wang, Wenping, Xie, Rong, Song, Li
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:https://arxiv.org/abs/2312.05295
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909326734524416
author Wang, Jionghao
Liu, Yuan
Dou, Zhiyang
Yu, Zhengming
Liang, Yongqing
Lin, Cheng
Li, Xin
Wang, Wenping
Xie, Rong
Song, Li
author_facet Wang, Jionghao
Liu, Yuan
Dou, Zhiyang
Yu, Zhengming
Liang, Yongqing
Lin, Cheng
Li, Xin
Wang, Wenping
Xie, Rong
Song, Li
contents In this paper, we introduce a novel text-to-avatar generation method that separately generates the human body and the clothes and allows high-quality animation on the generated avatar. While recent advancements in text-to-avatar generation have yielded diverse human avatars from text prompts, these methods typically combine all elements-clothes, hair, and body-into a single 3D representation. Such an entangled approach poses challenges for downstream tasks like editing or animation. To overcome these limitations, we propose a novel disentangled 3D avatar representation named Sequentially Offset-SMPL (SO-SMPL), building upon the SMPL model. SO-SMPL represents the human body and clothes with two separate meshes but associates them with offsets to ensure the physical alignment between the body and the clothes. Then, we design a Score Distillation Sampling (SDS)-based distillation framework to generate the proposed SO-SMPL representation from text prompts. Our approach not only achieves higher texture and geometry quality and better semantic alignment with text prompts, but also significantly improves the visual quality of character animation, virtual try-on, and avatar editing. Project page: https://shanemankiw.github.io/SO-SMPL/.
format Preprint
id arxiv_https___arxiv_org_abs_2312_05295
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Disentangled Clothed Avatar Generation from Text Descriptions
Wang, Jionghao
Liu, Yuan
Dou, Zhiyang
Yu, Zhengming
Liang, Yongqing
Lin, Cheng
Li, Xin
Wang, Wenping
Xie, Rong
Song, Li
Computer Vision and Pattern Recognition
In this paper, we introduce a novel text-to-avatar generation method that separately generates the human body and the clothes and allows high-quality animation on the generated avatar. While recent advancements in text-to-avatar generation have yielded diverse human avatars from text prompts, these methods typically combine all elements-clothes, hair, and body-into a single 3D representation. Such an entangled approach poses challenges for downstream tasks like editing or animation. To overcome these limitations, we propose a novel disentangled 3D avatar representation named Sequentially Offset-SMPL (SO-SMPL), building upon the SMPL model. SO-SMPL represents the human body and clothes with two separate meshes but associates them with offsets to ensure the physical alignment between the body and the clothes. Then, we design a Score Distillation Sampling (SDS)-based distillation framework to generate the proposed SO-SMPL representation from text prompts. Our approach not only achieves higher texture and geometry quality and better semantic alignment with text prompts, but also significantly improves the visual quality of character animation, virtual try-on, and avatar editing. Project page: https://shanemankiw.github.io/SO-SMPL/.
title Disentangled Clothed Avatar Generation from Text Descriptions
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.05295