Sequential Gaussian Avatars with Hierarchical Motion Context

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Wangze, Zhan, Yifan, Zhong, Zhihang, Sun, Xiao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908477387964416
author Xu, Wangze
Zhan, Yifan
Zhong, Zhihang
Sun, Xiao
author_facet Xu, Wangze
Zhan, Yifan
Zhong, Zhihang
Sun, Xiao
contents The emergence of neural rendering has significantly advanced the rendering quality of 3D human avatars, with the recently popular 3DGS technique enabling real-time performance. However, SMPL-driven 3DGS human avatars still struggle to capture fine appearance details due to the complex mapping from pose to appearance during fitting. In this paper, we propose SeqAvatar, which excavates the explicit 3DGS representation to better model human avatars based on a hierarchical motion context. Specifically, we utilize a coarse-to-fine motion conditions that incorporate both the overall human skeleton and fine-grained vertex motions for non-rigid deformation. To enhance the robustness of the proposed motion conditions, we adopt a spatio-temporal multi-scale sampling strategy to hierarchically integrate more motion clues to model human avatars. Extensive experiments demonstrate that our method significantly outperforms 3DGS-based approaches and renders human avatars orders of magnitude faster than the latest NeRF-based models that incorporate temporal context, all while delivering performance that is at least comparable or even superior. Project page: https://zezeaaa.github.io/projects/SeqAvatar/
format Preprint
id arxiv_https___arxiv_org_abs_2411_16768
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Sequential Gaussian Avatars with Hierarchical Motion Context
Xu, Wangze
Zhan, Yifan
Zhong, Zhihang
Sun, Xiao
Computer Vision and Pattern Recognition
The emergence of neural rendering has significantly advanced the rendering quality of 3D human avatars, with the recently popular 3DGS technique enabling real-time performance. However, SMPL-driven 3DGS human avatars still struggle to capture fine appearance details due to the complex mapping from pose to appearance during fitting. In this paper, we propose SeqAvatar, which excavates the explicit 3DGS representation to better model human avatars based on a hierarchical motion context. Specifically, we utilize a coarse-to-fine motion conditions that incorporate both the overall human skeleton and fine-grained vertex motions for non-rigid deformation. To enhance the robustness of the proposed motion conditions, we adopt a spatio-temporal multi-scale sampling strategy to hierarchically integrate more motion clues to model human avatars. Extensive experiments demonstrate that our method significantly outperforms 3DGS-based approaches and renders human avatars orders of magnitude faster than the latest NeRF-based models that incorporate temporal context, all while delivering performance that is at least comparable or even superior. Project page: https://zezeaaa.github.io/projects/SeqAvatar/
title Sequential Gaussian Avatars with Hierarchical Motion Context
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.16768