Diffusion Probabilistic Models for 3D Point Cloud Generation
arXiv:2103.01458
Abstract
We present a probabilistic model for point cloud generation, which is fundamental for various 3D vision tasks such as shape completion, upsampling, synthesis and data augmentation. Inspired by the diffusion process in non-equilibrium thermodynamics, we view points in point clouds as particles in a thermodynamic system in contact with a heat bath, which diffuse from the original distribution to a noise distribution. Point cloud generation thus amounts to learning the reverse diffusion process that transforms the noise distribution to the distribution of a desired shape. Specifically, we propose to model the reverse diffusion process for point clouds as a Markov chain conditioned on certain shape latent. We derive the variational bound in closed form for training and provide implementations of the model. Experimental results demonstrate that our model achieves competitive performance in point cloud generation and auto-encoding. The code is available at \url{https://github.com/luost26/diffusion-point-cloud}.
arXiv commentAccepted to CVPR 2021
References in corpus (9)
- Denoising Diffusion Probabilistic Models
- Deep Unsupervised Learning using Nonequilibrium Thermodynamics
- Equilibrium free energy differences from nonequilibrium measurements: a master equation approach
- Variational Inference with Normalizing Flows
- Density estimation using Real NVP
- Learning Representations and Generative Models for 3D Point Clouds
- FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
- Learning Gradient Fields for Shape Generation
- Discrete Point Flow Networks for Efficient Point Cloud Generation