Title: SHREC'20: Shape correspondence with non-isometric deformations - AIM@SHAPE (data)
Citation
Dyke RM, Lai Y, Rosin PL (2020). SHREC'20: Shape correspondence with non-isometric deformations - AIM@SHAPE (data). Cardiff University. https://doi.org/10.17035/d.2020.0112716358
Access Rights: Data can be made available only subject to certain contractual terms
Access Method: Click to email a request for this data to opendata@cardiff.ac.uk
Dataset Details
Publisher: Cardiff University
Date (year) of data becoming publicly available: 2020
Coverage start date: 18/02/2020
Coverage end date: 03/03/2020
Data format: .obj, .txt, .html
Software Required: MeshLab, CloudCompare, OpenFlipper
Estimated total storage size of dataset: Less than 100 megabytes
Number of Files In Dataset: 8
DOI : 10.17035/d.2020.0112716358
DOI URL: http://doi.org/10.17035/d.2020.0112716358
We have curated a dataset of 3D scans of objects from existing data repositories. All scans are of quadruped mammals. Shapes were primarily created using a variety of capturing techniques. Ground-truth corresdpondences were then established by three experts. Shapes (e.g., a giraffe and a dog) exhibit substantial non-isometric deformation, which prove challenging for existing shape matching methods. The dataset consists of both partial and watertight (i.e., full) meshes. Additional complexities caused by scanning, such as geometric and topological change, are also present. Pairs of shapes are assigned to test-sets of gradually increasing non-isometry. This dataset has been split into two parts to help make the licences clearer. This part contains the following shapes from the AIM@SHAPE-VISIONAIR Shape Repository: elephant_b, giraffe_b, cow, camel_a, camel_b, bear. Name in dataset Original name Author License Hyperlink elephant_b Livingstone elephant - full resolution, watertight, without auto-intersections AIM@SHAPE giraffe_b 390 wrl AIM@SHAPE cow 381 wrl AIM@SHAPE camel_a 17-Camel None* camel_b 140-Camel Free*+ bear 139-Bear Free*+ *When downloading these models you must still agree to the AIM@SHAPE General License for Shapes. +These models are also available from another source (http://www.wisdom.weizmann.ac.il/~vision/indexing/data.html) The Licence terms for these data are available at http://visionair.ge.imati.cnr.it/ontologies/shapes/download.jsp?id=803-Neptune_-_clean__watertight__4M_triangles_&classid=ManifoldSurfaceMesh&groupid=&type=original
Description
Keywords
3D Shape Retrieval, Shape correspondence
Related Projects
- Non-rigid registration of large-scale 3D deformations (01/10/2016 - 30/09/2020)