Weighted Multi-projection: 3D Point Cloud Denoising with Estimated Tangent Planes

TL;DR

This paper introduces a novel 3D point cloud denoising algorithm called weighted multi-projection, which estimates local tangent planes and reconstructs points through weighted averaging, improving accuracy over previous methods.

Contribution

The paper proposes a new denoising method that uses tangent plane estimation and multi-projection averaging, with theoretical analysis and superior empirical performance.

Findings

Outperforms competitors on ShapeNetCore dataset across nine classes

Provides tighter bounds for surface normal estimation

Demonstrates effective noise reduction in 3D point clouds

Abstract

As a collection of 3D points sampled from surfaces of objects, a 3D point cloud is widely used in robotics, autonomous driving and augmented reality. Due to the physical limitations of 3D sensing devices, 3D point clouds are usually noisy, which influences subsequent computations, such as surface reconstruction, recognition and many others. To denoise a 3D point cloud, we present a novel algorithm, called weighted multi-projection. Compared to many previous works on denoising, instead of directly smoothing the coordinates of 3D points, we use a two-fold smoothing: We first estimate a local tangent plane at each 3D point and then reconstruct each 3D point by weighted averaging of its projections on multiple tangent planes. We also provide the theoretical analysis for the surface normal estimation and achieve a tighter bound than in a previous work. We validate the empirical performance on the dataset of ShapeNetCore and show that weighted multi-projection outperforms its competitors in all nine classes.