NeuralQAAD: An Efficient Differentiable Framework for Compressing High Resolution Consistent Point Clouds Datasets

Nicolas Wagner, Ulrich Schwanecke

2022

Abstract

In this paper, we propose NeuralQAAD, a differentiable point cloud compression framework that is fast, robust to sampling, and applicable to consistent shapes with high detail resolution. Previous work that is able to handle complex and non-smooth topologies is hardly scaleable to more than just a few thousand points. We tackle the task with a novel neural network architecture characterized by weight sharing and autodecoding. Our architecture uses parameters far more efficiently than previous work, allowing it to be deeper and more scalable. We also show that the currently only tractable training criterion for point cloud compression, the Chamfer distance, performances poorly for high resolutions. To overcome this issue, we pair our architecture with a new training procedure based on a quadratic assignment problem. This procedure acts as a surrogate loss and allows to implicitly minimize the more expressive Earth Movers Distance (EMD) even for point clouds with way more than 106 points. As directly evaluating the EMD on high resolution point clouds is intractable, we propose a new divide-and-conquer approach based on k-d trees, which we call EM-kD. The EM-kD is shown to be a scaleable and fast but still reliable upper bound for the EMD. NeuralQAAD demonstrates on three datasets (COMA, D-FAUST and Skulls) that it significantly outperforms the current state-of-the-art both visually and qualitatively in terms of EM-kD.

Paper Citation

in Harvard Style

Wagner N. and Schwanecke U. (2022). NeuralQAAD: An Efficient Differentiable Framework for Compressing High Resolution Consistent Point Clouds Datasets. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP; ISBN 978-989-758-555-5, SciTePress, pages 811-822. DOI: 10.5220/0010772500003124

in Bibtex Style

@conference{visapp22,
author={Nicolas Wagner and Ulrich Schwanecke},
title={NeuralQAAD: An Efficient Differentiable Framework for Compressing High Resolution Consistent Point Clouds Datasets},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP},
year={2022},
pages={811-822},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010772500003124},
isbn={978-989-758-555-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP
TI - NeuralQAAD: An Efficient Differentiable Framework for Compressing High Resolution Consistent Point Clouds Datasets
SN - 978-989-758-555-5
AU - Wagner N.
AU - Schwanecke U.
PY - 2022
SP - 811
EP - 822
DO - 10.5220/0010772500003124
PB - SciTePress