Shape Correspondence with Isometric and Non-Isometric Deformations

Abstract
The registration of surfaces with non-rigid deformation, especially non-isometric deformations, is a challenging problem. When applying such techniques to real scans, the problem is compounded by topological and geometric inconsistencies between shapes. In this paper, we capture a benchmark dataset of scanned 3D shapes undergoing various controlled deformations (articulating, bending, stretching and topologically changing), along with ground truth correspondences. With the aid of this tiered benchmark of increasingly challenging real scans, we explore this problem and investigate how robust current state-of- the-art methods perform in different challenging registration and correspondence scenarios. We discover that changes in topology is a challenging problem for some methods and that machine learning-based approaches prove to be more capable of handling non-isometric deformations on shapes that are moderately similar to the training set.
Description

        
@inproceedings{
10.2312:3dor.20191069
, booktitle = {
Eurographics Workshop on 3D Object Retrieval
}, editor = {
Biasotti, Silvia and Lavoué, Guillaume and Veltkamp, Remco
}, title = {{
Shape Correspondence with Isometric and Non-Isometric Deformations
}}, author = {
Dyke, R. M.
 and
Stride, C.
 and
Groueix, T.
 and
Guo, D.
 and
Kim, V. G.
 and
Kimmel, R.
 and
Lähner, Z.
 and
Li, K.
 and
Litany, O.
 and
Remez, T.
 and
Rodolà, E.
 and
Russell, B. C.
 and
Lai, Y.-K.
 and
Sahillioglu, Y.
 and
Slossberg, R.
 and
Tam, G. K. L.
 and
Vestner, M.
 and
Wu, Z.
 and
Yang, J.
 and
Rosin, P. L.
 and
Aubry, M.
 and
Boyarski, A.
 and
Bronstein, A. M.
 and
Bronstein, M. M.
 and
Cremers, D.
 and
Fisher, M.
}, year = {
2019
}, publisher = {
The Eurographics Association
}, ISSN = {
1997-0471
}, ISBN = {
978-3-03868-077-2
}, DOI = {
10.2312/3dor.20191069
} }
Citation
Collections