Saved in:
Bibliographic Details
Main Authors: Wen, Jing, Zhao, Xiaoming, Ren, Zhongzheng, Schwing, Alexander G., Wang, Shenlong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.07991
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916201709436928
author Wen, Jing
Zhao, Xiaoming
Ren, Zhongzheng
Schwing, Alexander G.
Wang, Shenlong
author_facet Wen, Jing
Zhao, Xiaoming
Ren, Zhongzheng
Schwing, Alexander G.
Wang, Shenlong
contents We introduce GoMAvatar, a novel approach for real-time, memory-efficient, high-quality animatable human modeling. GoMAvatar takes as input a single monocular video to create a digital avatar capable of re-articulation in new poses and real-time rendering from novel viewpoints, while seamlessly integrating with rasterization-based graphics pipelines. Central to our method is the Gaussians-on-Mesh representation, a hybrid 3D model combining rendering quality and speed of Gaussian splatting with geometry modeling and compatibility of deformable meshes. We assess GoMAvatar on ZJU-MoCap data and various YouTube videos. GoMAvatar matches or surpasses current monocular human modeling algorithms in rendering quality and significantly outperforms them in computational efficiency (43 FPS) while being memory-efficient (3.63 MB per subject).
format Preprint
id arxiv_https___arxiv_org_abs_2404_07991
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh
Wen, Jing
Zhao, Xiaoming
Ren, Zhongzheng
Schwing, Alexander G.
Wang, Shenlong
Computer Vision and Pattern Recognition
We introduce GoMAvatar, a novel approach for real-time, memory-efficient, high-quality animatable human modeling. GoMAvatar takes as input a single monocular video to create a digital avatar capable of re-articulation in new poses and real-time rendering from novel viewpoints, while seamlessly integrating with rasterization-based graphics pipelines. Central to our method is the Gaussians-on-Mesh representation, a hybrid 3D model combining rendering quality and speed of Gaussian splatting with geometry modeling and compatibility of deformable meshes. We assess GoMAvatar on ZJU-MoCap data and various YouTube videos. GoMAvatar matches or surpasses current monocular human modeling algorithms in rendering quality and significantly outperforms them in computational efficiency (43 FPS) while being memory-efficient (3.63 MB per subject).
title GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.07991