Gaussian Control with Hierarchical Semantic Graphs in 3D Human Recovery

TL;DR

The paper introduces HUGS, a hierarchical graph-based framework that improves 3D human reconstruction by incorporating semantic priors and disentangling features, leading to more detailed and topologically consistent models.

Contribution

HUGS is the first to explicitly integrate semantic priors and hierarchical graphs for high-fidelity 3D human reconstruction, addressing geometric and topological challenges.

Findings

Superior surface detail reconstruction

Enhanced accuracy at body part junctions

Effective preservation of topological consistency

Abstract

Although 3D Gaussian Splatting (3DGS) has recently made progress in 3D human reconstruction, it primarily relies on 2D pixel-level supervision, overlooking the geometric complexity and topological relationships of different body parts. To address this gap, we introduce the Hierarchical Graph Human Gaussian Control (HUGS) framework for achieving high-fidelity 3D human reconstruction. Our approach involves leveraging explicitly semantic priors of body parts to ensure the consistency of geometric topology, thereby enabling the capture of the complex geometrical and topological associations among body parts. Additionally, we disentangle high-frequency features from global human features to refine surface details in body parts. Extensive experiments demonstrate that our method exhibits superior performance in human body reconstruction, particularly in enhancing surface details and accurately reconstructing body part junctions. Codes are available at https://wanghongsheng01.github.io/HUGS/.