A New 3D Shape Descriptor Based on Rotation

2006 ◽  
Author(s):  
Jeng-shyang Pan ◽  
Hao Luo ◽  
Zhe-ming Lu ◽  
Jung-chou Chang
Keyword(s):  
Shape Descriptor ◽  
3D Shape

scholarly journals 3D Shape Descriptor for Segmenting Point Cloud Data

2012 ◽  
Vol 30 (6_2) ◽  
pp. 643-651 ◽  
Author(s):  
So Young Park ◽  
Eun Jin Yoo ◽  
Dong-Cheon Lee ◽  
Yong Wook Lee
Keyword(s):  
Point Cloud ◽  
Shape Descriptor ◽  
Point Cloud Data ◽  
Cloud Data ◽  
3D Shape

scholarly journals A 3D shape descriptor based on spectral analysis of medial axis

2015 ◽  
Vol 39 ◽  
pp. 50-66 ◽  
Author(s):  
Shuiqing He ◽  
Yi-King Choi ◽  
Yanwen Guo ◽  
Xiaohu Guo ◽  
Wenping Wang
Keyword(s):  
Spectral Analysis ◽  
Medial Axis ◽  
Shape Descriptor ◽  
3D Shape

A new sizing system based on 3D shape descriptor for morphology clustering

2017 ◽  
Vol 113 ◽  
pp. 683-692 ◽  
Author(s):  
Moez Hamad ◽  
Sébastien Thomassey ◽  
Pascal Bruniaux
Keyword(s):  
Shape Descriptor ◽  
3D Shape ◽  
Sizing System

Learning a discriminative deformation-invariant 3D shape descriptor via many-to-one encoder

2016 ◽  
Vol 83 ◽  
pp. 330-338 ◽  
Author(s):  
Guoxian Dai ◽  
Jin Xie ◽  
Fan Zhu ◽  
Yi Fang
Keyword(s):  
Shape Descriptor ◽  
3D Shape

3D shape descriptor for object recognition based on Kinect-like depth image

2014 ◽  
Vol 32 (4) ◽  
pp. 260-269 ◽  
Author(s):  
M.A. As'ari ◽  
U.U. Sheikh ◽  
E. Supriyanto
Keyword(s):  
Object Recognition ◽  
Shape Descriptor ◽  
Depth Image ◽  
3D Shape

scholarly journals 3D Shape Completion with Multi-View Consistent Inference

2020 ◽  
Vol 34 (07) ◽  
pp. 10997-11004 ◽  
Author(s):  
Tao Hu ◽  
Zhizhong Han ◽  
Matthias Zwicker
Keyword(s):  
Point Clouds ◽  
Shape Descriptor ◽  
Depth Image ◽  
Regularization Term ◽  
3D Shape ◽  
Depth Images ◽  
3D Point Clouds ◽  
Geometric Consistency ◽  
Shape Completion ◽  
Data Term

3D shape completion is important to enable machines to perceive the complete geometry of objects from partial observations. To address this problem, view-based methods have been presented. These methods represent shapes as multiple depth images, which can be back-projected to yield corresponding 3D point clouds, and they perform shape completion by learning to complete each depth image using neural networks. While view-based methods lead to state-of-the-art results, they currently do not enforce geometric consistency among the completed views during the inference stage. To resolve this issue, we propose a multi-view consistent inference technique for 3D shape completion, which we express as an energy minimization problem including a data term and a regularization term. We formulate the regularization term as a consistency loss that encourages geometric consistency among multiple views, while the data term guarantees that the optimized views do not drift away too much from a learned shape descriptor. Experimental results demonstrate that our method completes shapes more accurately than previous techniques.

Application of the curvature scale space transform to the representation of three-dimensional models

2013 ◽  
Vol 18 (1) ◽  
pp. 23-29
Author(s):  
Dariusz Frejlichowski
Keyword(s):  
Computer Aided Design ◽  
Shape Representation ◽  
Three Dimensional ◽  
Shape Descriptor ◽  
3D Models ◽  
Scale Space ◽  
3D Shape ◽  
Three Dimensional Objects ◽  
Curvature Scale Space ◽  
Planar Shapes

Abstract In this paper an algorithm for the representation of 3D models is described and experimentally evaluated. Three-dimensional objects are becoming very popular recently and they are processed in various ways - analysed, retrieved, recognised, and so on. Moreover, they are employed in various aplications, such as virtual reality, entertainment, Internet, Computer Aided Design, or even in biometrics or medical imaging. That is why the development of appropriate algorithms for the representation of 3D objects is so important recently. These algorithms - so called 3D shape descriptors - are assumed to be invariant to particular transformations and deformations. One of the possible approaches is based on the projections of a 3D object into planar shapes and representation of them using a 2D shape descriptor. An algorithm realising this idea is described in this paper. Its first stage is based on the rendering of 20 2D projections, from various points of view. Later, the obtained projections are stored in a form of bitmaps and the Curvature Scale Space algorithm is applied for the description of the planar shapes extracted from them. The proposed approach is experimentally compared with several other 3D shape representation methods.

A 3D Shape Descriptor Based on Depth Complexity and Thickness Histograms

2015 ◽  
Author(s):  
Wagner Schmitt ◽  
Jose L. Sotomayor ◽  
Alexandru Telea ◽  
Claudio T. Silva ◽  
Joao L.D. Comba
Keyword(s):  
Shape Descriptor ◽  
3D Shape

A 3D shape descriptor based on spherical harmonics through evolutionary optimization

2016 ◽  
Vol 194 ◽  
pp. 183-191 ◽  
Author(s):  
Dingwen Wang ◽  
Shilei Sun ◽  
Xi Chen ◽  
Zhiwen Yu
Keyword(s):  
Spherical Harmonics ◽  
Shape Descriptor ◽  
Evolutionary Optimization ◽  
3D Shape
Sign in / Sign up

Export Citation Format

Share Document