MaskNet: A Fully-Convolutional Network to Estimate Inlier Points

10/19/2020
by   Vinit Sarode, et al.
52

Point clouds have grown in importance in the way computers perceive the world. From LIDAR sensors in autonomous cars and drones to the time of flight and stereo vision systems in our phones, point clouds are everywhere. Despite their ubiquity, point clouds in the real world are often missing points because of sensor limitations or occlusions, or contain extraneous points from sensor noise or artifacts. These problems challenge algorithms that require computing correspondences between a pair of point clouds. Therefore, this paper presents a fully-convolutional neural network that identifies which points in one point cloud are most similar (inliers) to the points in another. We show improvements in learning-based and classical point cloud registration approaches when retrofitted with our network. We demonstrate these improvements on synthetic and real-world datasets. Finally, our network produces impressive results on test datasets that were unseen during training, thus exhibiting generalizability. Code and videos are available at https://github.com/vinits5/masknet

READ FULL TEXT
research
10/24/2021

EgoNN: Egocentric Neural Network for Point Cloud Based 6DoF Relocalization at the City Scale

The paper presents a deep neural network-based method for global and loc...
research
10/31/2022

Point-Syn2Real: Semi-Supervised Synthetic-to-Real Cross-Domain Learning for Object Classification in 3D Point Clouds

Object classification using LiDAR 3D point cloud data is critical for mo...
research
10/18/2019

PointRNN: Point Recurrent Neural Network for Moving Point Cloud Processing

Point cloud is attracting more and more attention in the community. Howe...
research
03/21/2023

Smart-Tree: Neural Medial Axis Approximation of Point Clouds for 3D Tree Skeletonization

In this paper, we present Smart-Tree, a supervised method for approximat...
research
11/06/2017

Lisco: A Continuous Approach in LiDAR Point-cloud Clustering

The light detection and ranging (LiDAR) technology allows to sense surro...
research
03/27/2017

LIDAR-based Driving Path Generation Using Fully Convolutional Neural Networks

In this work, a novel learning-based approach has been developed to gene...
research
03/30/2019

USIP: Unsupervised Stable Interest Point Detection from 3D Point Clouds

In this paper, we propose the USIP detector: an Unsupervised Stable Inte...

Please sign up or login with your details

Forgot password? Click here to reset