3D Object Retrieval

The VCL group has developed several algorithms for 3D object descriptor extraction and application to 3D object retrieval. These algorithms have been experimentally evaluated using different benchmark datasets.

The first one was compiled from the Internet by us and it is called “the ITI database” (http://3d-test.iti.gr:8080/3d-test/download/ITI.zip). It consists of 544 3D models classified in 13 different categories: 27 animals, 17 spheroid objects, 64 conventional airplanes, 55 delta airplanes, 54 helicopters, 48 cars, 12 motorcycles, 10 tubes, 14 couches, 42 chairs, 45 fish, 53 humans, and 103 other models. This choice reflects primarily the shape of each object and secondarily its function. The average numbers of vertices and triangles of the models in the new database are 5080 and 7061, respectively.

The second dataset, the “Princeton Shape Benchmark (PSB)” (http://shape.cs.princeton.edu/benchmark/), was formed in Princeton University and it consists of 907 3D models classified into 35 main categories. This classification reflects primarily the function of each object and secondarily its form.

The third dataset, the “Engineering Shape Benchmark (ESB)” (https://engineering.purdue.edu/PRECISE/research/ShapeLab), contains a total of 867 3D CAD models from the mechanical engineering domain. They are classified into 3 main classes: 107 flat-thin wall components, 281 rectangular-cubic prism and 479 solids of revolution.

Additionally, several datasets of Shape Retrieval Contest (SHREC) have been used for evaluation of our algorithms. SHREC contest started in 2006 as an initiative of the AIM@SHAPE Network of Excellence (http://www.aimatshape.net/event/SHREC/), with the objective to evaluate the effectiveness of 3D-shape retrieval algorithms. The SHREC datasets used in our algorithms are given below:

 

Relevant papers

P. Daras, A. Axenopoulos, “A 3D Shape Retrieval Framework Supporting Multimodal Queries”, SPRINGER, International Journal of Computer Vision, DOI 10.1007/s11263-009-0277-2, Jul 2009.

D. Zarpalas, P. Daras, A. Axenopoulos, D. Tzovaras, M. G. Strintzis, “3D Model Search and Retrieval Using the Spherical Trace Transform”, Eurasip Journal on Advances in Signal Processing, Vol.2007, article ID 23912, 14 pages, Jan 2007, doi:10.1155/2007/23912.

P. Daras, A. Axenopoulos, G. Litos, “Investigating the Effects of Multiple Factors towards more Accurate 3D Object Retrieval”, IEEE Transactions on Multimedia, Vol. 14, No. 2, Page(s): 374 – 388, April 2012.

A. Axenopoulos, G. Litos, P. Daras, “3D Model Retrieval using Accurate Pose Estimation and View-based Similarity”, 1st ACM International Conference on Multimedia Retrieval (ICMR2011), April 17-20, Trento, Italy.

H. Dutagaci, A. Godil, P. Daras, A. Axenopoulos, G. Litos, S. Manolopoulou, K. Goto, T. Yanagimachi, Y. Kurita, S. Kawamura, T. Furuya, R. Ohbuchi, B. Gong, J. Liu, X. Tang, “SHREC’11 Track: Generic Shape Retrieval”, 4th Eurographics Workshop on 3D Object Retrieval (3DOR 2011), April 10, 2011, Llandudno (UK).

P. Daras, A. Axenopoulos, “A Compact Multi-View Descriptor for 3D Object Retrieval” IEEE 7th International Workshop on Content-Based Multimedia Indexing (CBMI 2009), Chania, Greece, Jun 2009.

C. Akgul, A. Axenopoulos, B. Bustos, M. Chaouch, P. Daras, H. Dutagaci, T. Furuya, A. Godil, S. Kreft, Z. Lian, T. Napoleon, A. Mademlis, R. Ohbuchi, P. L. Rosin, B. Sankur, T. Schreck, X. Sun, M. Tezuka, Y. Yemez, A. Verroust-Blondet, M.Walter, “SHREC 2009 – Generic Shape Retrieval Contest” 30th International conference on EUROGRAPHICS 2009, workshop on 3D object retrieval, Munich, Germany, Mar 2009.

A. Axenopoulos, P. Daras, H. Dutagaci, T. Furuya, A. Godil, R. Ohbuchi, “SHREC 2009 – Shape Retrieval Contest of Partial 3D Models” 30th International conference on EUROGRAPHICS 2009, Workshop on 3D object retrieval, Munich, Germany, Mar 2009.