DeepAI AI Chat
Log In Sign Up

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

08/30/2022
by   Anyi Huang, et al.
2

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.

READ FULL TEXT

page 2

page 3

page 4

page 7

page 8

page 10

page 11

10/28/2022

LBF:Learnable Bilateral Filter For Point Cloud Denoising

Bilateral filter (BF) is a fast, lightweight and effective tool for imag...
06/25/2022

BIMS-PU: Bi-Directional and Multi-Scale Point Cloud Upsampling

The learning and aggregation of multi-scale features are essential in em...
01/28/2022

Neighborhood-aware Geometric Encoding Network for Point Cloud Registration

The distinguishing geometric features determine the success of point clo...
10/13/2014

Multi-Scale Local Shape Analysis and Feature Selection in Machine Learning Applications

We introduce a method called multi-scale local shape analysis, or MLSA, ...
03/30/2021

Fast and Accurate Normal Estimation for Point Cloud via Patch Stitching

This paper presents an effective normal estimation method adopting multi...
02/17/2020

Large-Scale Evaluation of Shape-Aware Neighborhood Weights Neighborhood Sizes

Point sets arise naturally in many 3D acquisition processes and have div...

Code Repositories

MODNet

[Pacific Graphics 2022] MODNet: Multi-offset Point Cloud Denoising Network Customized for Multi-scale Patches


view repo