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

Abstract

Distortion quantification of point clouds plays a stealth, yet vital role in a wide range of human and machine perception tasks. For human perception tasks, a distortion quantification can substitute subjective experiments to guide 3D visualization; while for machine perception tasks, a distortion quantification can work as a loss function to guide the training of deep neural networks for unsupervised learning tasks. To handle a variety of demands in many applications, a distortion quantification needs to be distortion discriminable, differentiable, and have a low computational complexity. Currently, however, there is a lack of a general distortion quantification that can satisfy all three conditions. To fill this gap, this work proposes multiscale potential energy discrepancy (MPED), a distortion quantification to measure point cloud geometry and color difference. The proposed MPED is able to capture both geometrical and color impairments by quantifying the total distortion between reference and distorted samples. 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 experimental studies validate MPED's superiority for both human and machine perception tasks. For human perception tasks, the proposed MPED works as subjective score predictor. In terms of Spearman rank-order correlation coefficient, MPED is 4% to 35% better than other state-of-the-art distortion quantifications on SJTU-PCQA database, and 27% to 190% on LSPCQA database. For machine perception tasks, the proposed MPED is plugged in as the loss function to enable the training of deep neural networks for three tasks, including point cloud reconstruction, shape completion and upsampling. The experimental results reveal that the proposed MPED produces better results than the point-wise Chamfer distance and Earth Mover's distance under the same network architecture. For instance, in point cloud reconstruction, MPED is over 80% and 70% better than Chamfer distance and Earth Mover's distance in terms of Jensen-Shannon divergence, respectively. We further study the robustness and convergence rate of MPED in ablation study, and the results show that: i) MPED is robust to the variations in color space, neighborhood scale and spatial field; ii) MPED can converge to stable results with less training time and epochs using the same network model. Our code is avaliable at https://github.com/Qi-Yangsjtu/MPED.

Reduced Reference Quality Assessment for Point Cloud Compression

“…The results are shown in Table VI. [3] 0.61 0.58 H-PSNRyuv (FR) [33] 0.29 0.23 M-p2pl (FR) [34] 0.63 0.59 PCQM (FR) [12] 0.74 0.75 H-p2po (FR) [3] 0.51 0.46 GraphSIM (FR) [13] 0.74 0.75 H-p2pl (FR) [34] 0.55 0.48 MPED (FR) [35] 0.60 0.59 PSNRyuv (FR) [33] 0.46 0.47 PCM RR (RR) [16] 0.42 0.38 R-PCQA (RR) 0.88 0.88…”