Deep Point Cloud Simplification for High-quality Surface Reconstruction

TL;DR

This paper introduces PCS-Net, a novel deep learning method for simplifying point clouds to improve surface reconstruction quality by maintaining geometric fidelity and uniform point distribution.

Contribution

The paper presents a new point cloud simplification network that combines feature-aware sampling, double-scale resampling, and saliency-guided adaptive strategies for high-quality surface reconstruction.

Findings

Outperforms previous simplification methods in reconstruction quality.

Effectively preserves salient features while achieving uniform point distribution.

Enhances surface mesh reconstruction accuracy.

Abstract

The growing size of point clouds enlarges consumptions of storage, transmission, and computation of 3D scenes. Raw data is redundant, noisy, and non-uniform. Therefore, simplifying point clouds for achieving compact, clean, and uniform points is becoming increasingly important for 3D vision and graphics tasks. Previous learning based methods aim to generate fewer points for scene understanding, regardless of the quality of surface reconstruction, leading to results with low reconstruction accuracy and bad point distribution. In this paper, we propose a novel point cloud simplification network (PCS-Net) dedicated to high-quality surface mesh reconstruction while maintaining geometric fidelity. We first learn a sampling matrix in a feature-aware simplification module to reduce the number of points. Then we propose a novel double-scale resampling module to refine the positions of the sampled points, to achieve a uniform distribution. To further retain important shape features, an adaptive sampling strategy with a novel saliency loss is designed. With our PCS-Net, the input non-uniform and noisy point cloud can be simplified in a feature-aware manner, i.e., points near salient features are consolidated but still with uniform distribution locally. Experiments demonstrate the effectiveness of our method and show that we outperform previous simplification or reconstruction-oriented upsampling methods.