Generating Point Cloud Augmentations via Class-Conditioned Diffusion Model

In this paper, we present a class-conditioned Denoising Diffusion Probabilistic Model (DDPM) based approach to augment point cloud data within the latent feature space. Our method focuses on generating synthetic point cloud la-tent embeddings, which encode both spatial and semantic information of the point cloud. By harnessing the capabil-ities of DDPM within a class-conditioned framework, our goal is to provide a cost-effective and practical solution for the augmentation of point cloud samples. We conduct ex-periments on the publicly available point cloud dataset, and our findings suggest that the proposed approach (a) effectively generates high-quality synthetic embeddings directly from the Gaussian noise and (b) improves the classification performance of the point cloud classes within limited data settings.