MMApr 20

High-Fidelity 3D Gaussian Human Reconstruction via Region-Aware Initialization and Geometric Priors

arXiv:2604.2171451.3
AI Analysis

For interactive applications like VR and gaming, this method improves reconstruction quality and detail preservation over existing 3D Gaussian Splatting approaches.

The paper tackles high-fidelity 3D human reconstruction from RGB images, achieving superior reconstruction quality and finer detail preservation under complex motions while maintaining real-time rendering speed, as demonstrated on PeopleSnapshot and GalaBasketball datasets.

Real-time, high-fidelity 3D human reconstruction from RGB images is essential for interactive applications such as virtual reality and gaming, yet remains challenging due to the complex non-rigid deformations of dynamic human bodies. Although 3D Gaussian Splatting enables efficient rendering, existing methods struggle to capture fine geometric details and often produce artifacts such as fused fingers and over-smoothed faces. Moreover, conventional spatial-field-based dynamic modeling faces a trade-off between reconstruction fidelity and GPU memory consumption. To address these issues, we propose a novel 3D Gaussian human reconstruction framework that combines region-aware initialization with rich geometric priors. Specifically, we leverage the expressive SMPL-X model to initialize both 3D Gaussians and skinning weights, providing a robust geometric foundation for precise reconstruction. We further introduce a region-aware density initialization strategy and a geometry-aware multi-scale hash encoding module to improve local detail recovery while maintaining computational efficiency.Experiments on PeopleSnapshot and GalaBasketball show that our method achieves superior reconstruction quality and finer detail preservation under complex motions, while maintaining real-time rendering speed.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes