SHREC 2021: Retrieval of cultural heritage objects

Ivan Sipiran, Patrick Lazo, Cristian Lopez, Milagritos Jimenez, Nihar Bagewadi, Benjamin Bustos, Hieu Dao, Shankar Gangisetty, Martin Hanik, Ngoc Phuong Ho-Thi, Mike Holenderski, Dmitri Jarnikov, Arniel Labrada, Stefan Lengauer, Roxane Licandro, Dinh Huan Nguyen, Thang Long Nguyen-Ho, Luis A. Perez Rey, Bang Dang Pham, Minh Khoi PhamReinhold Preiner, Tobias Schreck, Quoc Huy Trinh, Loek Tonnaer, Christoph von Tycowicz, The Anh Vu-Le

Research output: Contribution to journalArticlepeer-review

Abstract

This paper presents the methods and results of the SHREC’21 track on a dataset of cultural heritage (CH) objects. We present a dataset of 938 scanned models that have varied geometry and artistic styles. For the competition, we propose two challenges: the retrieval-by-shape challenge and the retrieval-by-culture challenge. The former aims at evaluating the ability of retrieval methods to discriminate cultural heritage objects by overall shape. The latter focuses on assessing the effectiveness of retrieving objects from the same culture. Both challenges constitute a suitable scenario to evaluate modern shape retrieval methods in a CH domain. Ten groups participated in the challenges: thirty runs were submitted for the retrieval-by-shape task, and twenty-six runs were submitted for the retrieval-by-culture task. The results show a predominance of learning methods on image-based multi-view representations to characterize 3D objects. Nevertheless, the problem presented in our challenges is far from being solved. We also identify the potential paths for further improvements and give insights into the future directions of research.

Original languageEnglish
Pages (from-to)1-20
Number of pages20
JournalComputers and Graphics
Volume100
DOIs
StatePublished - Nov 2021
Externally publishedYes

Bibliographical note

Funding Information:
This work has been partially supported by Proyecto de Mejoramiento y Ampliación de los Servicios del Sistema Nacional de Ciencia, Tecnología e Innovación Tecnológica (Banco Mundial, Concytec), Nr. Grant 062-2018-FONDECYT-BM-IADT-AV. This work was supported by the European Commission (Bigmedilytics 780495, TRABIT 765148), the Austrian Research Promotion Agency (FFG) - BRIDGE (grant number: 878730), the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany’s Excellence Strategy The Berlin Mathematics Research Center MATH+ (EXC-2046/1, project ID: 390685689), the Bundesministerium fuer Bildung und Forschung (BMBF) through BIFOLD - The Berlin Institute for the Foundations of Learning and Data (ref. 01IS18025A and ref 01IS18037A). This work has also received funding from the NWO-TTW Programme “Efficient Deep Learning”(EDL) P16-25. The-Anh Vu-Le was funded by Vingroup Joint Stock Company and supported by the Domestic Master/ PhD Scholarship Programme of Vingroup Innovation Foundation (VINIF), Vingroup Big Data Institute (VINBIGDATA), code VINIF.2020.ThS.JVN.01. The HCMUS team was funded by Gia Lam Urban Development and Investment Company Limited, Vingroup and supported by Vingroup Innovation Foundation (VINIF) under project code VINIF.2019.DA19. This work was also co-funded by the Austrian Science Fund FWF and the State of Styria, Austria within the project Crossmodal Search and Visual Exploration of 3D Cultural Heritage Objects (P31317-NBL).

Funding Information:
This work has been partially supported by Proyecto de Mejoramiento y Ampliaci?n de los Servicios del Sistema Nacional de Ciencia, Tecnolog?a e Innovaci?n Tecnol?gica (Banco Mundial, Concytec), Nr. Grant 062-2018-FONDECYT-BM-IADT-AV. This work was supported by the European Commission (Bigmedilytics 780495, TRABIT 765148), the Austrian Research Promotion Agency (FFG) - BRIDGE (grant number: 878730), the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany's Excellence Strategy The Berlin Mathematics Research Center MATH+ (EXC-2046/1, project ID: 390685689), the Bundesministerium fuer Bildung und Forschung (BMBF) through BIFOLD - The Berlin Institute for the Foundations of Learning and Data (ref. 01IS18025A and ref 01IS18037A). This work has also received funding from the NWO-TTW Programme ?Efficient Deep Learning?(EDL) P16-25. The-Anh Vu-Le was funded by Vingroup Joint Stock Company and supported by the Domestic Master/ PhD Scholarship Programme of Vingroup Innovation Foundation (VINIF), Vingroup Big Data Institute (VINBIGDATA), code VINIF.2020.ThS.JVN.01. The HCMUS team was funded by Gia Lam Urban Development and Investment Company Limited, Vingroup and supported by Vingroup Innovation Foundation (VINIF) under project code VINIF.2019.DA19. This work was also co-funded by the Austrian Science Fund FWF and the State of Styria, Austria within the project Crossmodal Search and Visual Exploration of 3D Cultural Heritage Objects (P31317-NBL).

Publisher Copyright:
© 2021 Elsevier Ltd

Keywords

  • 3D model retrieval
  • Benchmarking
  • Cultural heritage

Fingerprint

Dive into the research topics of 'SHREC 2021: Retrieval of cultural heritage objects'. Together they form a unique fingerprint.

Cite this