Noise-resistant Deep Learning for Object Classification in 3D Point Clouds Using a Point Pair Descriptor

04/05/2018
by   Dmytro Bobkov, et al.
0

Object retrieval and classification in point cloud data is challenged by noise, irregular sampling density and occlusion. To address this issue, we propose a point pair descriptor that is robust to noise and occlusion and achieves high retrieval accuracy. We further show how the proposed descriptor can be used in a 4D convolutional neural network for the task of object classification. We propose a novel 4D convolutional layer that is able to learn class-specific clusters in the descriptor histograms. Finally, we provide experimental validation on 3 benchmark datasets, which confirms the superiority of the proposed approach.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/24/2017

Learning a 3D descriptor for cross-source point cloud registration from synthetic data

As the development of 3D sensors, registration of 3D data (e.g. point cl...
research
07/18/2023

SphereNet: Learning a Noise-Robust and General Descriptor for Point Cloud Registration

Point cloud registration is to estimate a transformation to align point ...
research
07/25/2023

Mini-PointNetPlus: a local feature descriptor in deep learning model for 3d environment perception

Common deep learning models for 3D environment perception often use pill...
research
05/21/2018

Spherical Convolutional Neural Network for 3D Point Clouds

We propose a neural network for 3D point cloud processing that exploits ...
research
02/27/2020

Triangle-Net: Towards Robustness in Point Cloud Classification

3D object recognition is becoming a key desired capability for many comp...
research
05/05/2023

Persistent Homology Meets Object Unity: Object Recognition in Clutter

Recognition of occluded objects in unseen and unstructured indoor enviro...
research
05/16/2022

Topologically Persistent Features-based Object Recognition in Cluttered Indoor Environments

Recognition of occluded objects in unseen indoor environments is a chall...

Please sign up or login with your details

Forgot password? Click here to reset