SHREC 2020 Track: Non-rigid Shape Correspondence of Physically-Based Deformations

dc.contributor.authorDyke, Roberto M.en_US
dc.contributor.authorZhou, Fengen_US
dc.contributor.authorLai, Yu-Kunen_US
dc.contributor.authorRosin, Paul L.en_US
dc.contributor.authorGuo, Daoliangen_US
dc.contributor.authorLi, Kunen_US
dc.contributor.authorMarin, Riccardoen_US
dc.contributor.authorYang, Jingyuen_US
dc.contributor.editorSchreck, Tobias and Theoharis, Theoharis and Pratikakis, Ioannis and Spagnuolo, Michela and Veltkamp, Remco C.en_US
dc.date.accessioned2020-09-03T09:50:26Z
dc.date.available2020-09-03T09:50:26Z
dc.date.issued2020
dc.description.abstractCommonly, novel non-rigid shape correspondence techniques focus on particular matching challenges. This can lead to the potential trade-off of poorer performance in other scenarios. An ideal dataset would provide a granular means for degrees of evaluation. In this paper, we propose a novel dataset of real scans that contain challenging non-isometric deformations to evaluate non-rigid point-to-point correspondence and registration algorithms. The deformations included in our dataset cover extreme types of physically-based contortions of a toy rabbit. Furthermore, shape pairs contain incrementally different types and amounts of deformation, this enables performance to be systematically evaluated with respect to the nature of the deformation. A brief investigation into different methods for initialising correspondence was undertaken, and a series of experiments were subsequently conducted to investigate the performance of state-of-the-art methods on the proposed dataset. We find that methods that rely on initial correspondences and local descriptors that are sensitive to local surface changes perform poorly in comparison to other strategies, and that a template-based approach performs the best.en_US
dc.description.sectionheadersSHREC Short Papers
dc.description.seriesinformationEurographics Workshop on 3D Object Retrieval
dc.identifier.doi10.2312/3dor.20201161
dc.identifier.isbn978-3-03868-126-7
dc.identifier.issn1997-0471
dc.identifier.pages19-26
dc.identifier.urihttps://doi.org/10.2312/3dor.20201161
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/3dor20201161
dc.publisherThe Eurographics Associationen_US
dc.subjectComputing methodologies
dc.subjectShape analysis
dc.subjectMesh models
dc.titleSHREC 2020 Track: Non-rigid Shape Correspondence of Physically-Based Deformationsen_US
Files