HoloTetSphere: Unified TetSphere Mesh Reconstruction for Physical Simulations

2026-07-09

AI Summary

This work proposes the first end-to-end, topology-adaptive tetrahedral mesh reconstruction framework that directly generates high-quality meshes suitable for physics simulation. Traditional physics-ready 3D reconstruction pipelines rely on decoupled surface extraction and tetrahedralization, often introducing errors, while existing methods like TetSphere are constrained by homeomorphism assumptions and struggle with topological changes, leading to disconnected meshes. In contrast, the proposed approach couples Gaussian splats with tetrahedral elements, estimating a continuous opacity field via edge connectivity to enable differentiable pruning. It jointly optimizes multi-view Gaussian rendering loss and mesh smoothness energy through alternating steps of geometric refinement and topology preservation. This strategy significantly improves geometric accuracy and ensures single-connectedness, circumventing error accumulation inherent in conventional two-stage pipelines.

Abstract

Standard pipelines for physics-ready 3D reconstruction rely on a decoupled two-stage paradigm: extracting surface geometry followed by an error-prone tetrahedralization process. While recent Lagrangian methods like TetSphere Splatting attempt to bypass this by directly optimizing volumetric primitives, their homeomorphic constraints prevent topology-adaptive optimization. Consequently, they produce disjoint tetrahedra rather than a single connected mesh, rendering the structures unsuitable for further physical simulations. To address this, we propose a topology-adaptive framework for holistic tetrahedral mesh reconstruction through end-to-end topological and geometric optimization. First, by coupling Gaussian spheres to tetrahedral elements and leveraging edge connections, we estimate a continuous opacity field for differentiable element pruning. Next, jointly minimizing mesh smoothing energy and multi-view Gaussian rendering error drives alternating geometric refinement while preserving topological adaptivity. Consequently, our approach effectively constructs a unified and topologically coherent tetrahedral mesh. Extensive experiments demonstrate that our method outperforms state-of-the-art techniques by achieving superior geometric accuracy and producing coherent, single-connected tetrahedral meshes, thereby effectively bypassing the error-prone conventional tetrahedralization step for reconstructed surface meshes and streamlining downstream physical simulation.

Problem

• tetrahedral mesh
• topology adaptation
• physical simulation
• 3D reconstruction
• mesh connectivity

Innovation

• topology-adaptive
• tetrahedral mesh
• end-to-end optimization
• Gaussian splatting
• physical simulation