English

Cluster-Based Autoencoders for Volumetric Point Clouds

Computer Vision and Pattern Recognition 2022-11-03 v1

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.

Keywords

Cite

@article{arxiv.2211.01009,
  title  = {Cluster-Based Autoencoders for Volumetric Point Clouds},
  author = {Stephan Antholzer and Martin Berger and Tobias Hell},
  journal= {arXiv preprint arXiv:2211.01009},
  year   = {2022}
}
R2 v1 2026-06-28T05:00:02.881Z