Cluster-Based Autoencoders for Volumetric Point Clouds

TL;DR

This paper introduces a clustering-based autoencoder approach for volumetric point clouds, enabling high-resolution input processing and applications like blending and style transfer while maintaining shape integrity.

Contribution

It presents a novel clustering and reassembling method combined with a FoldingNet-based autoencoder for volumetric point clouds, enhancing high-resolution data handling.

Findings

Enables high-resolution volumetric point cloud reconstruction.

Facilitates blending between high-resolution point clouds.

Supports style transfer while preserving shape.

Abstract

Autoencoders allow to reconstruct a given input from a small set of parameters. However, the input size is often limited due to computational costs. We therefore propose a clustering and reassembling method for volumetric point clouds, in order to allow high resolution data as input. We furthermore present an autoencoder based on the well-known FoldingNet for volumetric point clouds and discuss how our approach can be utilized for blending between high resolution point clouds as well as for transferring a volumetric design/style onto a pointcloud while maintaining its shape.