Foreword to the special section on 3D Object Retrieval 2020 workshop (3DOR2020)

The aim of the 3D Object Retrieval (3DOR) Workshop series is to provide a premier venue for research in 3D / 4D visual content search, exploration and understanding for researchers from diverse fields such as Computer Vision, Computer Graphics, Machine Learning, Cognitive Science and Human-Computer Interaction. In addition, the Shape Retrieval Contest (SHREC) is an established venue for benchmarking new and existing methods in shape retrieval. SHREC and 3DOR have been running together since 2009 with SHREC being the benchmarking arm of 3DOR and 3DOR being the dissemination and networking arm of SHREC.

3DOR 2020 was the 13th workshop in the 3DOR series. It took place on the 4th and 5th of September 2020. The planned physical venue was TU Graz, Austria, but due to the outbreak of COVID-19, it was converted to a virtual event hosted by TU Graz. The workshop was free to all, supported by the 3DOR endowment.

The main novelty introduced in 2020 was the possibility to publish submitted manuscripts directly in the Elsevier Computers & Graphics (C&G) journal; to make this happen the full paper submission track followed a 2-stage review process. A second call for submissions of short papers took place and a selection of these papers was published in the Eurographics Digital Library, which hosts all the 3DOR proceedings. The workshop programme featured 16 presentations. We were pleased to have Professor Stefano Berretti, University of Florence, as Keynote Speaker who gave an inspiring talk on “3D Face modeling and Reconstruction”.

18 papers were submitted to the full paper track, out of which 9 were accepted for publication in Computers & Graphics; 3 of these papers applied and received the Replicability Badge issued by the Graphics Replicability Stamp Initiative (GRSI). Of these 9 papers, 4 were research papers while 5 were the outcome of SHREC tracks.

Research full papers (4). In [1] a benchmark for detailed 3D gesture detection and recognition is presented and used to evaluate two proposed methods. 3D segmentation, correspondence and mapping are used to improve the visualization of anatomical structures in [2]. Multimodal 3D registration methods are extensively surveyed in [3], while attempting to categorize them independent of application domain. A new local shape descriptor is presented in [4] which, along with its distance function, is shown to be clutter resistant; an indexing scheme for such binary descriptors is also presented.

SHREC full papers (5). A simulated dataset of 3D cryo-electron tomograms was made available in [5] where the task was to localize and identify certain protein structures; 6 research groups participated with 7 methods in total. In [6] semantic segmentation methods are evaluated based on a street scene dataset of 80 scenes with over 2 million triangles each, along with ground truth segmentations of 5 classes: building, car, ground, pole and vegetation; 4 groups participated in this challenge with their methods, most of which used machine learning. Protein retrieval based on their 3D shape was addressed in [7] using a dataset of 588 proteins; 6 groups participated with 15 method variations in total. Methods for the retrieval of objects based on their surface geometric relief patterns were evaluated in [8]; such methods are useful, e.g., in the classification of cultural heritage fragments and the organizers provided a dataset of 220 surfaces with 11 different reliefs; 7 groups participated in the evaluation with at least 1 method variation each. Non-isometric deformations for shape correspondence continues to be a challenging problem and the authors of this track [9] used a library of corresponding animal shapes with highly non-isometric deformations; ground-truth correspondences have been labelled by experts and 10 methods were submitted for evaluation.

We would like to thank the IPC members for their reviewing efforts, which helped us to create a high-quality program. We also thank the Eurographics Association for their continued support, TU Graz for hosting the virtual event, the 3DOR endowment for sponsorship, Stefanie Behnke (EG publishing) for her support in managing the workshop, Stefan Lengauer (TU Graz) for technical support, and Joaquim Jorge, editor-in-chief of C&G for making this C&G Special Section possible.

Biographies

Tobias Schreck is a Professor and head of the Institute of Computer Graphics and Knowledge Visualization at Graz University of Technology, Austria. Between 2011 and 2015, he was an Assistant Professor with University of Konstanz, Germany. Between 2007 and 2011, he was a Postdoc researcher and head of group at Technische Universität Darmstadt, Germany. He obtained a PhD in Computer Science in 2006, and a Master of Science degree in Information Engineering in 2002, both from the University of Konstanz. Tobias Schreck works in the areas of Visual Analytics, Information Visualization, and 3D Object Retrieval.

Theoharis Theoharis received his D.Phil. in computer graphics and parallel processing from the University of Oxford, UK in 1988. He subsequently served as a research fellow at the University of Cambridge, UK, a Professor at the University of Athens, Greece and at NTNU, Norway. His main research interests lie in the fields of 3D Object Retrieval, Biometrics and Reconstruction. He is the author of a number of textbooks, including “Graphics and Visualization: principles and algorithms” (A K Peters/CRC Press, 2008).  See http://www.idi.ntnu.no/grupper/vis/

Ioannis Pratikakis is Professor at the Department of Electrical and Computer Engineering at Democritus University of Thrace in Xanthi, Greece. He received the Ph.D. degree in 3D Image analysis from the Electronics engineering and Informatics department at Vrije Universiteit Brussel, Belgium, in January 1999. From March 1999 to March 2000, he joined IRISA in Rennes, France as an INRIA postdoctoral fellow. From January 2003 to June 2010, he was working as Adjunct Researcher at the Institute of Informatics and Telecommunications in the National Centre for Scientific Research “Demokritos”, Athens, Greece. His research interests lie in image processing, pattern recognition, vision and graphics, and more specifically, in document image analysis and recognition, medical image analysis as well as 3D shape analysis, search and retrieval. He has published more than 200 papers in journals, book chapters and conference proceedings in the above areas for which he has received more than 7400 references with h-index:47 (source: Google Scholar). He has served as Guest editor in several journals including the International Journal of Computer Vision, The Visual Computer as well as the Computers & Graphics. He currently serves as Associate Editor for the MDPI Journal of imaging and the Springer Nature Computer Science journal. He is member of the steering committee of EG Workshop on 3D Object Retrieval. He has been member of the Board of the Hellenic Artificial Intelligence Society for the period 2010–2014. He is Senior Member of the IEEE, member of the board of IEEE Greece Section (2013–2019) and member of the European Association for Computer Graphics (Eurographics).

Michela Spagnuolo is Research Director at the National Research Council of Italy, and currently Director of the Institute of Applied Mathematics and Information Technologies. Her current interests include 3D shape analysis techniques, shape similarity and matching, uncertainty coding in 3D data sets, and computational topology. She authored more than 150 reviewed papers, and is a member of the steering committee of the EG workshop on 3D Object Retrieval, EG Workshop on Graphics and Cultural Heritage, and Shape Modelling International. She is associate editor of IEEE Trans. on Visualization and Computer Graphics, Computer-Aided Geometric Design, Computers&Graphics and The Visual Computer.

Remco C. Veltkamp is full professor of Game and Media Technology at Utrecht University, The Netherlands. His research topics are the analysis, recognition and retrieval of, and interaction with, 3D objects and scenes, images, video, music, and games. His interests are in particular the algorithmic and experimentation aspects, with a special focus on game research. He is director of the Utrecht center for Game Research, http://www.gameresearch.nl/, he has published over 250 refereed papers in journals and conferences, and supervised 24 PhD. theses.