Shape Correspondence with Isometric and Non-Isometric Deformations
| dc.contributor.author | Dyke, R. M. | en_US |
| dc.contributor.author | Stride, C. | en_US |
| dc.contributor.author | Lai, Y.-K. | en_US |
| dc.contributor.author | Rosin, P. L. | en_US |
| dc.contributor.author | Aubry, M. | en_US |
| dc.contributor.author | Boyarski, A. | en_US |
| dc.contributor.author | Bronstein, A. M. | en_US |
| dc.contributor.author | Bronstein, M. M. | en_US |
| dc.contributor.author | Cremers, D. | en_US |
| dc.contributor.author | Fisher, M. | en_US |
| dc.contributor.author | Groueix, T. | en_US |
| dc.contributor.author | Guo, D. | en_US |
| dc.contributor.author | Kim, V. G. | en_US |
| dc.contributor.author | Kimmel, R. | en_US |
| dc.contributor.author | Lähner, Z. | en_US |
| dc.contributor.author | Li, K. | en_US |
| dc.contributor.author | Litany, O. | en_US |
| dc.contributor.author | Remez, T. | en_US |
| dc.contributor.author | Rodolà, E. | en_US |
| dc.contributor.author | Russell, B. C. | en_US |
| dc.contributor.author | Sahillioglu, Y. | en_US |
| dc.contributor.author | Slossberg, R. | en_US |
| dc.contributor.author | Tam, G. K. L. | en_US |
| dc.contributor.author | Vestner, M. | en_US |
| dc.contributor.author | Wu, Z. | en_US |
| dc.contributor.author | Yang, J. | en_US |
| dc.contributor.editor | Biasotti, Silvia and Lavoué, Guillaume and Veltkamp, Remco | en_US |
| dc.date.accessioned | 2019-05-04T14:06:06Z | |
| dc.date.available | 2019-05-04T14:06:06Z | |
| dc.date.issued | 2019 | |
| dc.description.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. | en_US |
| dc.description.sectionheaders | SHREC Session 2 | |
| dc.description.seriesinformation | Eurographics Workshop on 3D Object Retrieval | |
| dc.identifier.doi | 10.2312/3dor.20191069 | |
| dc.identifier.isbn | 978-3-03868-077-2 | |
| dc.identifier.issn | 1997-0471 | |
| dc.identifier.pages | 111-119 | |
| dc.identifier.uri | https://doi.org/10.2312/3dor.20191069 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.2312/3dor20191069 | |
| dc.publisher | The Eurographics Association | en_US |
| dc.subject | Theory of computation | |
| dc.subject | Computational geometry | |
| dc.subject | Computing methodologies | |
| dc.subject | Mesh geometry models | |
| dc.subject | Shape analysis | |
| dc.title | Shape Correspondence with Isometric and Non-Isometric Deformations | en_US |
Files
Original bundle
1 - 1 of 1