TexVocab: Texture Vocabulary-conditioned Human Avatars

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Yuxiao, Li, Zhe, Liu, Yebin, Wang, Haoqian
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913292803375104
author Liu, Yuxiao
Li, Zhe
Liu, Yebin
Wang, Haoqian
author_facet Liu, Yuxiao
Li, Zhe
Liu, Yebin
Wang, Haoqian
contents To adequately utilize the available image evidence in multi-view video-based avatar modeling, we propose TexVocab, a novel avatar representation that constructs a texture vocabulary and associates body poses with texture maps for animation. Given multi-view RGB videos, our method initially back-projects all the available images in the training videos to the posed SMPL surface, producing texture maps in the SMPL UV domain. Then we construct pairs of human poses and texture maps to establish a texture vocabulary for encoding dynamic human appearances under various poses. Unlike the commonly used joint-wise manner, we further design a body-part-wise encoding strategy to learn the structural effects of the kinematic chain. Given a driving pose, we query the pose feature hierarchically by decomposing the pose vector into several body parts and interpolating the texture features for synthesizing fine-grained human dynamics. Overall, our method is able to create animatable human avatars with detailed and dynamic appearances from RGB videos, and the experiments show that our method outperforms state-of-the-art approaches. The project page can be found at https://texvocab.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2404_00524
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TexVocab: Texture Vocabulary-conditioned Human Avatars
Liu, Yuxiao
Li, Zhe
Liu, Yebin
Wang, Haoqian
Computer Vision and Pattern Recognition
To adequately utilize the available image evidence in multi-view video-based avatar modeling, we propose TexVocab, a novel avatar representation that constructs a texture vocabulary and associates body poses with texture maps for animation. Given multi-view RGB videos, our method initially back-projects all the available images in the training videos to the posed SMPL surface, producing texture maps in the SMPL UV domain. Then we construct pairs of human poses and texture maps to establish a texture vocabulary for encoding dynamic human appearances under various poses. Unlike the commonly used joint-wise manner, we further design a body-part-wise encoding strategy to learn the structural effects of the kinematic chain. Given a driving pose, we query the pose feature hierarchically by decomposing the pose vector into several body parts and interpolating the texture features for synthesizing fine-grained human dynamics. Overall, our method is able to create animatable human avatars with detailed and dynamic appearances from RGB videos, and the experiments show that our method outperforms state-of-the-art approaches. The project page can be found at https://texvocab.github.io/.
title TexVocab: Texture Vocabulary-conditioned Human Avatars
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.00524