A Point Cloud Generative Model Based on Nonequilibrium Thermodynamics

Shitong Luo, Wei Hu

Keywords: Point cloud, Generation, Generative model

Abstract: We present a probabilistic model for point cloud generation, which is critical 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 the state-of-the-art performance in point cloud generation and auto-encoding.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: We propose a novel probabilistic model for point cloud generation inspired by nonequilibrium thermodynamics, achieving the state-of-the-art performance.

Reviewed Version (pdf): https://openreview.net/references/pdf?id=DxqwOORL2-