4 papers
NeuralSSD: A Neural Solver for Signed Distance Surface Reconstruction
Zi-Chen Xi, Jiahui Huang, Hao-Xiang Chen +4
We proposed a generalized method, NeuralSSD, for reconstructing a 3D implicit surface from the widely-available point cloud data. NeuralSSD is a solver-based on the neural Galerkin…
SCube: Instant Large-Scale Scene Reconstruction using VoxSplats
Xuanchi Ren, Yifan Lu, Hanxue Liang +6
We present SCube, a novel method for reconstructing large-scale 3D scenes (geometry, appearance, and semantics) from a sparse set of posed images. Our method encodes reconstructed…
Approximately Piecewise E(3) Equivariant Point Networks
Matan Atzmon, Jiahui Huang, Francis Williams +1
Integrating a notion of symmetry into point cloud neural networks is a provably effective way to improve their generalization capability. Of particular interest are equivari…
XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies
Xuanchi Ren, Jiahui Huang, Xiaohui Zeng +3
We present XCube (abbreviated as ), a novel generative model for high-resolution sparse 3D voxel grids with arbitrary attributes. Our model can generate millions of…