TGA: True-to-Geometry Avatar Dynamic Reconstruction
Bo Guo, Sijia Wen, Ziwei Wang, Yifan Zhao
Abstract
Recent advances in 3D Gaussian Splatting (3DGS) have improved the visual fidelity of dynamic avatar reconstruction. However, existing methods often overlook the inherent chromatic similarity of human skin tones, leading to poor capture of intricate facial geometry under subtle appearance changes. This is caused by the affine approximation of Gaussian projection, which fails to be perspective-aware to depth-induced shear effects. To this end, we propose True-to-Geometry Avatar Dynamic Reconstruction (TGA), a perspective-aware 4D Gaussian avatar framework that sensitively captures fine-grained facial variations for accurate 3D geometry reconstruction. Specifically, to enable color-sensitive and geometry-consistent Gaussian representations under dynamic conditions, we introduce Perspective-Aware Gaussian Transformation that jointly models temporal deformations and spatial projection by integrating Jacobian-guided adaptive deformation into the homogeneous formulation. Furthermore, we develop Incremental BVH Tree Pivoting to enable fast frame-by-frame mesh extraction for 4D Gaussian representations. A dynamic Gaussian Bounding Volume Hierarchy (BVH) tree is used to model the topological relationships among points, where active ones are filtered out by BVH pivoting and subsequently re-triangulated for surface reconstruction. Extensive experiments demonstrate that TGA achieves superior geometric accuracy.
BibTeX
@inproceedings{
guo2025tga,
title={{TGA}: True-to-Geometry Avatar Dynamic Reconstruction},
author={Bo Guo and Sijia Wen and Ziwei Wang and Yifan Zhao},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=EyFrTjaYU3}
}