English

Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modeling

Computer Vision and Pattern Recognition 2025-06-13 v3

Abstract

High-fidelity 3D object synthesis remains significantly more challenging than 2D image generation due to the unstructured nature of mesh data and the cubic complexity of dense volumetric grids. Existing two-stage pipelines-compressing meshes with a VAE (using either 2D or 3D supervision), followed by latent diffusion sampling-often suffer from severe detail loss caused by inefficient representations and modality mismatches introduced in VAE. We introduce Sparc3D, a unified framework that combines a sparse deformable marching cubes representation Sparcubes with a novel encoder Sparconv-VAE. Sparcubes converts raw meshes into high-resolution (102431024^3) surfaces with arbitrary topology by scattering signed distance and deformation fields onto a sparse cube, allowing differentiable optimization. Sparconv-VAE is the first modality-consistent variational autoencoder built entirely upon sparse convolutional networks, enabling efficient and near-lossless 3D reconstruction suitable for high-resolution generative modeling through latent diffusion. Sparc3D achieves state-of-the-art reconstruction fidelity on challenging inputs, including open surfaces, disconnected components, and intricate geometry. It preserves fine-grained shape details, reduces training and inference cost, and integrates naturally with latent diffusion models for scalable, high-resolution 3D generation.

Keywords

Cite

@article{arxiv.2505.14521,
  title  = {Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modeling},
  author = {Zhihao Li and Yufei Wang and Heliang Zheng and Yihao Luo and Bihan Wen},
  journal= {arXiv preprint arXiv:2505.14521},
  year   = {2025}
}

Comments

Homepage: https://lizhihao6.github.io/Sparc3D

R2 v1 2026-07-01T02:25:31.743Z