Pointfilter: Point Cloud Filtering via Encoder-Decoder Modeling

02/14/2020
by   Dongbo Zhang, et al.
0

Point cloud filtering is a fundamental problem in geometry modeling and processing. Despite of advancement in recent years, the existing methods still suffer from two issues: they are either designed without preserving sharp features or less robust in preserving geometric features; they usually have many parameters and require tedious parameter tuning. In this paper, we propose a novel deep learning approach that automatically and robustly filters point clouds with removing noise and preserving sharp features and geometric details. Our point-wise learning architecture consists of an encoder and a decoder. The encoder directly takes points (a point and its neighbors) as input, and learns a latent representation vector which is gone through the decoder and related to the ground-truth position. Our trained network can automatically infer a corresponding quality point set to a noisy point cloud input. Extensive evaluations show that our approach outperforms the state-of-the-art deep learning techniques in terms of visual quality and error metrics. We will make our code and dataset publicly available.

READ FULL TEXT

page 3

page 4

page 5

page 7

page 8

page 9

page 10

page 12

research
04/24/2020

Deep Feature-preserving Normal Estimation for Point Cloud Filtering

Point cloud filtering, the main bottleneck of which is removing noise (o...
research
08/14/2022

Contrastive Learning for Joint Normal Estimation and Point Cloud Filtering

Point cloud filtering and normal estimation are two fundamental research...
research
05/17/2023

Tinto: Multisensor Benchmark for 3D Hyperspectral Point Cloud Segmentation in the Geosciences

The increasing use of deep learning techniques has reduced interpretatio...
research
04/27/2022

Density-preserving Deep Point Cloud Compression

Local density of point clouds is crucial for representing local details,...
research
07/14/2023

A Dynamic Points Removal Benchmark in Point Cloud Maps

In the field of robotics, the point cloud has become an essential map re...
research
12/14/2020

DSM Refinement with Deep Encoder-Decoder Networks

3D city models can be generated from aerial images. However, the calcula...
research
07/13/2021

PU-Flow: a Point Cloud Upsampling Networkwith Normalizing Flows

Point cloud upsampling aims to generate dense point clouds from given sp...

Please sign up or login with your details

Forgot password? Click here to reset