3D object representations have become an integral part of modern computer graphics applications, such as computer-aided design, game development and film production. At the same time, 3D data have become very common in domains such as computer vision, computational geometry, molecular biology and medicine. The rapid evolution in graphics hardware and software development, in particular the availability of low cost 3D scanners, has greatly facilitated 3D model acquisition, creation and manipulation, giving the opportunity to experience applications using 3D models to a large user community

As the number of 3D models is rapidly growing, the main issue in the field has shifted from the creation of new 3D models to the retrieval of existing 3D models. Thereupon, the development of efficient search mechanisms is required for the effective retrieval of 3D objects from large repositories, both of a single class (such as human faces) and across classes.

The aim of this project is the study, design and implementation of novel robust and effective methodologies for the retrieval of static and spatio-temporal 3D objects. Global 3D shape descriptors will be explored: pose normalization exploiting geometric object features including symmetry; invariant features for rigid objects; use of 2D queries for 3D object retrieval. To generalize the applicability of 3D object retrieval for non-rigid objects, retrieval using a part-based representation will be addressed using hierarchical segmentation methods along with both global and partial matching methodologies.

3D object retrieval will also be addressed in the case of dynamic spatio-temporal entities appearing in 3D videos. Novel spatio-temporal shape descriptors will be investigated in the context of two specific use cases: dynamic 3D face retrieval and dynamic action retrieval of 3D humans. The proposed research will be continuously evaluated using existing as well as novel evaluation methodologies coupled with new 3D databases.


3DOR / MIS: 379516

Project info

Coordinating Institution:
Democritus University of Thrace (DUTH)
Scientific Coordinator:
Pratikakis Ioannis
Research Team 1 Leader:
Pratikakis Ioannis
Research Team 2 Leader:
Theoharis Theoharis
Research Team 3 Leader:
Chamzas Christopoulos


Duration (months):
586 293.00
ΑΔΑ: Β41Ρ9-Δ5Γ

Document Library