MPED: Quantifying Point Cloud Distortion based on Multiscale Potential Energy Discrepancy

TL;DR

This paper introduces MPED, a multiscale distortion quantification method for point clouds that is differentiable, discriminative, and computationally efficient, improving both perception and learning tasks.

Contribution

The paper proposes a novel point cloud distortion metric, MPED, based on potential energy discrepancy, which unifies and improves upon existing methods by capturing multiscale distortions.

Findings

MPED outperforms existing distortion metrics in perception tasks.

Classical Chamfer distance is a special case of MPED.

MPED is effective for both dense and sparse point cloud applications.

Abstract

In this paper, we propose a new distortion quantification method for point clouds, the multiscale potential energy discrepancy (MPED). Currently, there is a lack of effective distortion quantification for a variety of point cloud perception tasks. Specifically, for dense point clouds, a distortion quantification method is used to predict human subjective scores and optimize the selection of human perception tasks parameters, such as compression and enhancement. For sparse point clouds, a distortion quantification methods is work as a loss function to guide the training of deep neural networks for unsupervised learning tasks (e.g., point cloud reconstruction, completion and upsampling). Therefore, an effective distortion quantification should be differentiable, distortion discriminable and have a low computational complexity. However, current distortion quantification cannot satisfy all three conditions. To fill this gap, we propose a new point cloud feature description method, the point potential energy (PPE), inspired by the classical physics. We regard the point clouds are systems that have potential energy and the distortion can change the total potential energy. By evaluating at various neighborhood sizes, the proposed MPED achieves global-local tradeoffs, capturing distortion in a multiscale fashion. We further theoretically show that classical Chamfer distance is a special case of our MPED. Extensive experiments show the proposed MPED superior to current methods on both human and machine perception tasks. Our code is avaliable at https://github.com/Qi-Yangsjtu/MPED.