scholarly journals Spline Positional Encoding for Learning 3D Implicit Signed Distance Fields

2021 ◽  
Author(s):  
Peng-Shuai Wang ◽  
Yang Liu ◽  
Yu-Qi Yang ◽  
Xin Tong
Keyword(s):  
Dimensional Space ◽  
Point Clouds ◽  
Shape Space ◽  
Shape Reconstruction ◽  
Multilayer Perceptrons ◽  
3D Shape ◽  
Signed Distance ◽  
Distance Fields ◽  
3D Point Clouds ◽  
3D Shape Reconstruction

Multilayer perceptrons (MLPs) have been successfully used to represent 3D shapes implicitly and compactly, by mapping 3D coordinates to the corresponding signed distance values or occupancy values. In this paper, we propose a novel positional encoding scheme, called Spline Positional Encoding, to map the input coordinates to a high dimensional space before passing them to MLPs, which help recover 3D signed distance fields with fine-scale geometric details from unorganized 3D point clouds. We verified the superiority of our approach over other positional encoding schemes on tasks of 3D shape reconstruction and 3D shape space learning from input point clouds. The efficacy of our approach extended to image reconstruction is also demonstrated and evaluated.

scholarly journals Shape Registration with Learned Deformations for 3D Shape Reconstruction from Sparse and Incomplete Point Clouds

2021 ◽  
pp. 102228
Author(s):  
Xiang Chen ◽  
Nishant Ravikumar ◽  
Yan Xia ◽  
Rahman Attar ◽  
Andres Diaz-Pinto ◽  
...  
Keyword(s):  
Point Clouds ◽  
Shape Reconstruction ◽  
3D Shape ◽  
Shape Registration ◽  
3D Shape Reconstruction

scholarly journals 3D Object Shape Reconstruction from Underwater Multibeam Data and Over Ground Lidar Scanning

2018 ◽  
Vol 25 (2) ◽  
pp. 47-56 ◽  
Author(s):  
Marek Kulawiak ◽  
Zbigniew Łubniewski
Keyword(s):  
Laser Scanning ◽  
Spatial Information ◽  
Dimensional Space ◽  
Three Dimensional ◽  
Measurement Data ◽  
Point Clouds ◽  
Shape Reconstruction ◽  
Reconstruction Algorithms ◽  
Processing Scheme ◽  
3D Shape Reconstruction

Abstract The technologies of sonar and laser scanning are an efficient and widely used source of spatial information with regards to underwater and over ground environment respectively. The measurement data are usually available in the form of groups of separate points located irregularly in three-dimensional space, known as point clouds. This data model has known disadvantages, therefore in many applications a different form of representation, i.e. 3D surfaces composed of edges and facets, is preferred with respect to the terrain or seabed surface relief as well as various objects shape. In the paper, the authors propose a new approach to 3D shape reconstruction from both multibeam and LiDAR measurements. It is based on a multiple-step and to some extent adaptive process, in which the chosen set and sequence of particular stages may depend on a current type and characteristic features of the processed data. The processing scheme includes: 1) pre-processing which may include noise reduction, rasterization and pre-classification, 2) detection and separation of objects for dedicated processing (e.g. steep walls, masts), and 3) surface reconstruction in 3D by point cloud triangulation and with the aid of several dedicated procedures. The benefits of using the proposed methods, including algorithms for detecting various features and improving the regularity of the data structure, are presented and discussed. Several different shape reconstruction algorithms were tested in combination with the proposed data processing methods and the strengths and weaknesses of each algorithm were highlighted.

scholarly journals A Divide et Impera Approach for 3D Shape Reconstruction from Multiple Views

2020 ◽  
Author(s):  
Riccardo Spezialetti ◽  
David Joseph Tan ◽  
Alessio Tonioni ◽  
Keisuke Tateno ◽  
Federico Tombari
Keyword(s):  
Shape Reconstruction ◽  
Multiple Views ◽  
3D Shape ◽  
3D Shape Reconstruction
Sign in / Sign up

Export Citation Format

Share Document