Neighborhood-aware Geometric Encoding Network for Point Cloud Registration

01/28/2022
by   Lifa Zhu, et al.
6

The distinguishing geometric features determine the success of point cloud registration. However, most point clouds are partially overlapping, corrupted by noise, and comprised of indistinguishable surfaces, which makes it a challenge to extract discriminative features. Here, we propose the Neighborhood-aware Geometric Encoding Network (NgeNet) for accurate point cloud registration. NgeNet utilizes a geometric guided encoding module to take geometric characteristics into consideration, a multi-scale architecture to focus on the semantically rich regions in different scales, and a consistent voting strategy to select features with proper neighborhood size and reject the specious features. The awareness of adaptive neighborhood points is obtained through the multi-scale architecture accompanied by voting. Specifically, the proposed techniques in NgeNet are model-agnostic, which could be easily migrated to other networks. Comprehensive experiments on indoor, outdoor and object-centric synthetic datasets demonstrate that NgeNet surpasses all of the published state-of-the-art methods. The code will be available at https://github.com/zhulf0804/NgeNet.

READ FULL TEXT

page 3

page 7

page 16

page 18

research
01/07/2021

Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds

Boundary information plays a significant role in 2D image segmentation, ...
research
08/09/2023

PointMBF: A Multi-scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud Registration

Point cloud registration is a task to estimate the rigid transformation ...
research
03/26/2021

3D Point Cloud Registration with Multi-Scale Architecture and Self-supervised Fine-tuning

We present MS-SVConv, a fast multi-scale deep neural network that output...
research
02/23/2022

Reliable Inlier Evaluation for Unsupervised Point Cloud Registration

Unsupervised point cloud registration algorithm usually suffers from the...
research
08/18/2023

DReg-NeRF: Deep Registration for Neural Radiance Fields

Although Neural Radiance Fields (NeRF) is popular in the computer vision...
research
08/30/2022

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

The intricacy of 3D surfaces often results cutting-edge point cloud deno...
research
09/12/2023

SGFeat: Salient Geometric Feature for Point Cloud Registration

Point Cloud Registration (PCR) is a critical and challenging task in com...

Please sign up or login with your details

Forgot password? Click here to reset