Gaussian Control with Hierarchical Semantic Graphs in 3D Human Recovery
This work improves 3D human reconstruction for applications like animation or virtual reality, but it is incremental as it builds on 3D Gaussian Splatting by incorporating semantic priors.
The paper tackles the problem of 3D human reconstruction by addressing the oversight of geometric complexity and topological relationships in existing methods, resulting in superior performance with enhanced surface details and accurate reconstruction of body part junctions.
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/.