MODNet: Multi-offset Point Cloud Denoising Network Customized for Multi-scale Patches

TL;DR

MODNet introduces a multi-offset point cloud denoising network that adaptively utilizes multi-scale geometric information to improve surface detail preservation and reduce degradation in noisy 3D data.

Contribution

The paper proposes a novel multi-offset denoising network with a multi-scale perception module that adaptively guides feature utilization based on local geometry.

Findings

Achieves state-of-the-art results on synthetic datasets.

Outperforms existing methods on real-scanned data.

Effectively preserves geometric details near edges and complex surfaces.

Abstract

The intricacy of 3D surfaces often results cutting-edge point cloud denoising (PCD) models in surface degradation including remnant noise, wrongly-removed geometric details. Although using multi-scale patches to encode the geometry of a point has become the common wisdom in PCD, we find that simple aggregation of extracted multi-scale features can not adaptively utilize the appropriate scale information according to the geometric information around noisy points. It leads to surface degradation, especially for points close to edges and points on complex curved surfaces. We raise an intriguing question -- if employing multi-scale geometric perception information to guide the network to utilize multi-scale information, can eliminate the severe surface degradation problem? To answer it, we propose a Multi-offset Denoising Network (MODNet) customized for multi-scale patches. First, we extract the low-level feature of three scales patches by patch feature encoders. Second, a multi-scale perception module is designed to embed multi-scale geometric information for each scale feature and regress multi-scale weights to guide a multi-offset denoising displacement. Third, a multi-offset decoder regresses three scale offsets, which are guided by the multi-scale weights to predict the final displacement by weighting them adaptively. Experiments demonstrate that our method achieves new state-of-the-art performance on both synthetic and real-scanned datasets.