Enhancing Diffusion-based Point Cloud Generation with Smoothness Constraint

TL;DR

This paper introduces a method to improve diffusion-based point cloud generation by incorporating a smoothness constraint, resulting in more realistic and surface-smooth point clouds.

Contribution

The paper proposes a novel approach that integrates local smoothness constraints into diffusion models for enhanced point cloud generation.

Findings

Generated point clouds are more realistic and smooth.

Outperforms existing state-of-the-art methods.

Produces higher quality surface details.

Abstract

Diffusion models have been popular for point cloud generation tasks. Existing works utilize the forward diffusion process to convert the original point distribution into a noise distribution and then learn the reverse diffusion process to recover the point distribution from the noise distribution. However, the reverse diffusion process can produce samples with non-smooth points on the surface because of the ignorance of the point cloud geometric properties. We propose alleviating the problem by incorporating the local smoothness constraint into the diffusion framework for point cloud generation. Experiments demonstrate the proposed model can generate realistic shapes and smoother point clouds, outperforming multiple state-of-the-art methods.