3D Object Retrieval (3DOR)

As 3D object collections grow in size, due to 3D capture applications and the wider availability of 3D scanners, content-based retrieval grows in importance. 3DOR involves the creation of descriptors that represent the shape and other characteristics of a 3D object in an accurate and compact manner.

A growing number of applications benefit from 3DOR technologies, since they can be cast as inter- or intra-class retrieval problems. These include:

  • 👥

    3D Biometrics, e.g. 3D face recognition

    For more information on our work with 3D biomestrics,  e.g. 3D face recognition see our Biometrics page.

  • Object reassembly from parts

    Our team worked with object reassembly from parts. An example application for archaeology can be found at our page about the PRESIOUS project.

  • Parts retrieval

    Retrieval of 3D objects for large industrial applications.

  • 🔍

    Object recognition

Our team has been active since the inception of this field.

We have jointly set-up and serve on the Steering Committee of the 3D Object Retrieval workshop series (3DOR), which is usually hosted in conjunction with the Eurographics conference.

🎓

We have jointly organised Special Issues in 3D Object Retrieval in journals such as:

Sample publications:

Danelakis A., T. Theoharis, I. Pratikakis & P. Perakis, ‘An Effective Methodology for Dynamic 3D Facial Expression Retrieval’, Pattern Recognition, 52, April 2016, pp. 174-185.

Sfikas K., T. Theoharis, I. Pratikakis, ‘ROSy+: 3D Object Pose Normalization based on PCA and Reflective Object Symmetry with Application in 3D Object Retrieval’, International Journal of Computer Vision (IJCV), 91(3), February 2011, pp. 262-279.

Papadakis P., I. Pratikakis, T. Theoharis and S. Perantonis, ‘PANORAMA: A 3D Shape Descriptor based on Panoramic Views for Unsupervised 3D Object Retrieval’, International Journal of Computer Vision (IJCV), 89(2/3), September 2010, pp. 177-192.