Non-Rigid 3D Mesh Registration Integrated with a Linearisable Curvature Term

Non-rigid registration is an issue since it is indisposed with high Degrees Of Freedom (DOF) and hence, it is low sensitivity to highlights of Source surface. We introduce a non-rigid registration technique integrated with a new shape descriptor inspired by Gaussian curvature in the cost function, and define the corresponding points locally based on mixture of distance and the curvature values. We formulate the energy function with the curvature, stiffness, and distance term, and try to tackle issue of both distance and the curvature for corresponding points. Likewise, corresponding point is chosen amongst adjustable number of nearest points with less value of summation of normalized both distance and curvature. Experimental results indicate that high curved specifications of original surface are better saved compared to the conventional method.

Authors

Institutions

Publication Details

Published
2024-12-25
DOI
https://doi.org/10.1109/icspis65223.2024.10931107
Citations
1
Primary Topic
3D Shape Modeling and Analysis
Type
article
Field-Weighted Citation Impact
0.37
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Non-Rigid 3D Mesh Registration Integrated with a Linearisable Curvature Term

Amin Rezasoltani, Farzam Tajdari
1 citations
3D Shape Modeling and Analysis
0.37
article

Non-Rigid 3D Mesh Registration Integrated with a Linearisable Curvature Term

Amin Rezasoltani, Farzam Tajdari
article en
1 citations

Abstract

Non-rigid registration is an issue since it is indisposed with high Degrees Of Freedom (DOF) and hence, it is low sensitivity to highlights of Source surface. We introduce a non-rigid registration technique integrated with a new shape descriptor inspired by Gaussian curvature in the cost function, and define the corresponding points locally based on mixture of distance and the curvature values. We formulate the energy function with the curvature, stiffness, and distance term, and try to tackle issue of both distance and the curvature for corresponding points. Likewise, corresponding point is chosen amongst adjustable number of nearest points with less value of summation of normalized both distance and curvature. Experimental results indicate that high curved specifications of original surface are better saved compared to the conventional method.

Delft University of Technology (NL)
Openalex Percentile: Top 39%
3D Shape Modeling and Analysis
0.37
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.