Point Cloud Upsampling and Normal Estimation using Deep Learning for Robust Surface Reconstruction

02/26/2021
by   Rajat Sharma, et al.
0

The reconstruction of real-world surfaces is on high demand in various applications. Most existing reconstruction approaches apply 3D scanners for creating point clouds which are generally sparse and of low density. These points clouds will be triangulated and used for visualization in combination with surface normals estimated by geometrical approaches. However, the quality of the reconstruction depends on the density of the point cloud and the estimation of the surface normals. In this paper, we present a novel deep learning architecture for point cloud upsampling that enables subsequent stable and smooth surface reconstruction. A noisy point cloud of low density with corresponding point normals is used to estimate a point cloud with higher density and appendant point normals. To this end, we propose a compound loss function that encourages the network to estimate points that lie on a surface including normals accurately predicting the orientation of the surface. Our results show the benefit of estimating normals together with point positions. The resulting point cloud is smoother, more complete, and the final surface reconstruction is much closer to ground truth.

READ FULL TEXT

page 6

page 8

research
09/22/2020

Implicit reconstructions of thin leaf surfaces from large, noisy point clouds

Thin surfaces, such as the leaves of a plant, pose a significant challen...
research
01/03/2019

GeoNet: Deep Geodesic Networks for Point Cloud Analysis

Surface-based geodesic topology provides strong cues for object semantic...
research
04/24/2020

DPDist : Comparing Point Clouds Using Deep Point Cloud Distance

We introduce a new deep learning method for point cloud comparison. Our ...
research
04/13/2017

Denoising a Point Cloud for Surface Reconstruction

Surface reconstruction from an unorganized point cloud is an important p...
research
11/23/2021

Deep Point Cloud Reconstruction

Point cloud obtained from 3D scanning is often sparse, noisy, and irregu...
research
04/28/2021

D-OccNet: Detailed 3D Reconstruction Using Cross-Domain Learning

Deep learning based 3D reconstruction of single view 2D image is becomin...
research
07/01/2018

Weighted Multi-projection: 3D Point Cloud Denoising with Estimated Tangent Planes

As a collection of 3D points sampled from surfaces of objects, a 3D poin...

Please sign up or login with your details

Forgot password? Click here to reset