SMPLX-Lite: A Realistic and Drivable Avatar Benchmark with Rich Geometry and Texture Annotations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jiang, Yujiao, Liao, Qingmin, Wang, Zhaolong, Lin, Xiangru, Lu, Zongqing, Zhao, Yuxi, Wei, Hanqing, Ye, Jingrui, Zhang, Yu, Shao, Zhijing
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Graphics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866916265774284800
author	Jiang, Yujiao Liao, Qingmin Wang, Zhaolong Lin, Xiangru Lu, Zongqing Zhao, Yuxi Wei, Hanqing Ye, Jingrui Zhang, Yu Shao, Zhijing
author_facet	Jiang, Yujiao Liao, Qingmin Wang, Zhaolong Lin, Xiangru Lu, Zongqing Zhao, Yuxi Wei, Hanqing Ye, Jingrui Zhang, Yu Shao, Zhijing
contents	Recovering photorealistic and drivable full-body avatars is crucial for numerous applications, including virtual reality, 3D games, and tele-presence. Most methods, whether reconstruction or generation, require large numbers of human motion sequences and corresponding textured meshes. To easily learn a drivable avatar, a reasonable parametric body model with unified topology is paramount. However, existing human body datasets either have images or textured models and lack parametric models which fit clothes well. We propose a new parametric model SMPLX-Lite-D, which can fit detailed geometry of the scanned mesh while maintaining stable geometry in the face, hand and foot regions. We present SMPLX-Lite dataset, the most comprehensive clothing avatar dataset with multi-view RGB sequences, keypoints annotations, textured scanned meshes, and textured SMPLX-Lite-D models. With the SMPLX-Lite dataset, we train a conditional variational autoencoder model that takes human pose and facial keypoints as input, and generates a photorealistic drivable human avatar.
format	Preprint
id	arxiv_https___arxiv_org_abs_2405_19609
institution	arXiv
publishDate	2024
record_format	arxiv
spellingShingle	SMPLX-Lite: A Realistic and Drivable Avatar Benchmark with Rich Geometry and Texture Annotations Jiang, Yujiao Liao, Qingmin Wang, Zhaolong Lin, Xiangru Lu, Zongqing Zhao, Yuxi Wei, Hanqing Ye, Jingrui Zhang, Yu Shao, Zhijing Computer Vision and Pattern Recognition Graphics Recovering photorealistic and drivable full-body avatars is crucial for numerous applications, including virtual reality, 3D games, and tele-presence. Most methods, whether reconstruction or generation, require large numbers of human motion sequences and corresponding textured meshes. To easily learn a drivable avatar, a reasonable parametric body model with unified topology is paramount. However, existing human body datasets either have images or textured models and lack parametric models which fit clothes well. We propose a new parametric model SMPLX-Lite-D, which can fit detailed geometry of the scanned mesh while maintaining stable geometry in the face, hand and foot regions. We present SMPLX-Lite dataset, the most comprehensive clothing avatar dataset with multi-view RGB sequences, keypoints annotations, textured scanned meshes, and textured SMPLX-Lite-D models. With the SMPLX-Lite dataset, we train a conditional variational autoencoder model that takes human pose and facial keypoints as input, and generates a photorealistic drivable human avatar.
title	SMPLX-Lite: A Realistic and Drivable Avatar Benchmark with Rich Geometry and Texture Annotations
topic	Computer Vision and Pattern Recognition Graphics
url	https://arxiv.org/abs/2405.19609