We have produced a new dataset from 3D scans of real-world objects, captured by ourselves using a high-precision 3D scanner (Artec3D Space Spider) designed for small objects. Each object exhibits one or more types of deformation. We classify these surface deformations into four distinct groups by level of complexity: 1.) articulating, 2.) bending, 3.) stretching, 4.) geometrically and topologically changing. The dataset consists of scans of wooden mannequins and wooden hands that are articulated. Further types of deformation are produced by, creating clothes for the model from different fabrics.
Report of research results based upon these data can be found at http://orca.cf.ac.uk/121530/
Funding
Non-rigid registration of large-scale 3D deformations (2016-10-01 - 2020-09-30); Dyke, Roberto. Funder: Engineering and Physical Sciences Research Council