Latent-Space Laplacian Pyramids for Adversarial Representation Learning with 3D Point Clouds

TL;DR

This paper introduces a hierarchical generative model using latent-space Laplacian pyramids to produce high-resolution 3D point clouds with finer details, outperforming existing models.

Contribution

It combines latent-space GAN and Laplacian GAN architectures into a multi-scale model for detailed 3D point cloud generation, a novel approach in the field.

Findings

Outperforms existing 3D point cloud generative models

Capable of generating multi-scale, high-resolution 3D shapes

Demonstrates improved detail and quality in generated 3D surfaces

Abstract

Constructing high-quality generative models for 3D shapes is a fundamental task in computer vision with diverse applications in geometry processing, engineering, and design. Despite the recent progress in deep generative modelling, synthesis of finely detailed 3D surfaces, such as high-resolution point clouds, from scratch has not been achieved with existing approaches. In this work, we propose to employ the latent-space Laplacian pyramid representation within a hierarchical generative model for 3D point clouds. We combine the recently proposed latent-space GAN and Laplacian GAN architectures to form a multi-scale model capable of generating 3D point clouds at increasing levels of detail. Our evaluation demonstrates that our model outperforms the existing generative models for 3D point clouds.