Search papers, labs, and topics across Lattice.
This paper introduces HoloTetSphere, a novel framework for unified tetrahedral mesh reconstruction that integrates topological and geometric optimization to overcome limitations of traditional two-stage pipelines. By coupling Gaussian spheres with tetrahedral elements and minimizing both mesh smoothing energy and multi-view Gaussian rendering error, the method ensures the production of a single, coherent tetrahedral mesh suitable for physical simulations. Extensive experiments show that HoloTetSphere significantly outperforms existing techniques, achieving higher geometric accuracy and eliminating the conventional tetrahedralization step that often introduces errors.
Traditional tetrahedralization is error-prone, but HoloTetSphere achieves a unified, coherent mesh that enhances physical simulation accuracy.
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.
