3D Shape Generation and Completion through Point-Voxel Diffusion
Authors:
- Yilun DuYDYilun Du
Top Cited Papers
- 1 October 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5806-5815
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. PVD marries 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.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- 3D Volumetric Modeling with Introspective Neural NetworksProceedings of the AAAI Conference on Artificial Intelligence, 2019
- PartNet: A Large-Scale Benchmark for Fine-Grained and Hierarchical Part-Level 3D Object Understanding2019
- VoxSegNet: Volumetric CNNs for Semantic Part Segmentation of 3D ShapesIEEE Transactions on Visualization and Computer Graphics, 2019
- PointGrid: A Deep Network for 3D Shape Understanding2018
- Learning Descriptor Networks for 3D Shape Synthesis and Analysis2018
- FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation2018
- DeformNet: Free-Form Deformation Network for 3D Shape Reconstruction from a Single Image2018
- Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs2017
- A Point Set Generation Network for 3D Object Reconstruction from a Single Image2017
- VoxNet: A 3D Convolutional Neural Network for real-time object recognition2015