3D Shape Generation and Completion Through Point-Voxel Diffusion

Linqi Zhou, Yilun Du, Jiajun Wu; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 5826-5835

Abstract


We propose a novel approach for probabilistic generative modeling of 3D shapes. Unlike most existing models that learn to deterministically translate a latent vector to a shape, our model, Point-Voxel Diffusion (PVD), is a unified, probabilistic formulation for unconditional shape generation and conditional, multi-modal shape completion. PVDmarries denoising diffusion models with the hybrid, point-voxel representation of 3D shapes. It can be viewed as a series of denoising steps, reversing the diffusion process from observed point cloud data to Gaussian noise, and is trained by optimizing a variational lower bound to the (conditional) likelihood function. Experiments demonstrate that PVD is capable of synthesizing high-fidelity shapes, completing partial point clouds, and generating multiple completion results from single-view depth scans of real objects.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2021_ICCV, author = {Zhou, Linqi and Du, Yilun and Wu, Jiajun}, title = {3D Shape Generation and Completion Through Point-Voxel Diffusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {5826-5835} }