Increasing the Capability of Neural Networks for Surface Reconstruction from Noisy Point Clouds

11/29/2018
by   Adam R White, et al.
0

This paper builds upon the current methods to increase their capability and automation for 3D surface construction from noisy and potentially sparse point clouds. It presents an analysis of an artificial neural network surface regression and mapping method, describing caveats, improvements and justification for the different approach.

READ FULL TEXT
research
11/18/2021

Learning Modified Indicator Functions for Surface Reconstruction

Surface reconstruction is a fundamental problem in 3D graphics. In this ...
research
07/16/2018

EC-Net: an Edge-aware Point set Consolidation Network

Point clouds obtained from 3D scans are typically sparse, irregular, and...
research
04/22/2022

PU-EVA: An Edge Vector based Approximation Solution for Flexible-scale Point Cloud Upsampling

High-quality point clouds have practical significance for point-based re...
research
05/28/2019

Controlling Neural Level Sets

The level sets of neural networks represent fundamental properties such ...
research
07/30/2021

Out-of-Core Surface Reconstruction via Global TGV Minimization

We present an out-of-core variational approach for surface reconstructio...
research
08/18/2021

Quality assessment of image matchers for DSM generation – a comparative study based on UAV images

Recently developed automatic dense image matching algorithms are now bei...
research
12/08/2020

Planet cartography with neural learned regularization

Finding potential life harboring exo-Earths is one of the aims of exopla...

Please sign up or login with your details

Forgot password? Click here to reset