A Comparison of Methods for 3D Scene Shape Retrieval

Authors

Juefei Yuan, University of Southern MississippiFollow
Hameed Abdul-Rashid, University of Southern MississippiFollow
Bo Li, University of Southern MississippiFollow
Yijuan Lu, Texas State UniversityFollow
Tobias Schreck, Technische Universitat Graz
Song Bai, Huazhong University of Science and TechnologyFollow
Xiang Bai, Huazhong University of Science and TechnologyFollow
Ngoc Minh Bui, Viet Nam National University Ho Chi Minh City
Minh N. Do, University of Illinois at Urbana-Champaign
Trong Le Do, Viet Nam National University Ho Chi Minh City
Anh Duc Duong, Viet Nam National University Ho Chi Minh CityFollow
Kai He, University of Southern Mississippi
Xinwei He, Huazhong University of Science and Technology
Mike Holenderski, Technische Universiteit Eindhoven
Dmitri Jarnikov, Technische Universiteit Eindhoven
Tu Khiem Le, Viet Nam National University Ho Chi Minh City
Wenhui Li, Tianjin UniversityFollow
Anan Liu, Tianjin UniversityFollow
Xiaolong Liu, Huazhong University of Science and TechnologyFollow
Vlado Menkovski, Technische Universiteit Eindhoven
Khac Tuan Nguyen, Viet Nam National University Ho Chi Minh City
Thanh An Nguyen, Viet Nam National University Ho Chi Minh City
Vinh Tiep Nguyen, Viet Nam National University Ho Chi Minh City
Weizhi Nie, Tianjin University
Van Tu Ninh, Viet Nam National University Ho Chi Minh City
Perez Rey, Technische Universiteit Eindhoven
Yuting Su, Tianjin UniversityFollow
Vinh Ton-That, Viet Nam National University Ho Chi Minh City
Minh Triet Tran, Viet Nam National University Ho Chi Minh CityFollow
Tianyang Wang, Austin Peay State University
Shu Xiang, Tianjin University
Shandian Zhe, The University of Utah
Heyu Zhou, Tianjin University

Document Type

Article

Publication Date

12-1-2020

School

Computing Sciences and Computer Engineering

Abstract

© 2020 Elsevier Inc. 3D scene shape retrieval is a brand new but important research direction in content-based 3D shape retrieval. To promote this research area, two Shape Retrieval Contest (SHREC) tracks on 2D scene sketch-based and image-based 3D scene model retrieval have been organized by us in 2018 and 2019, respectively. In 2018, we built the first benchmark for each track which contains 2D and 3D scene data for ten (10) categories, while they share the same 3D scene target dataset. Four and five distinct 3D scene shape retrieval methods have competed with each other in these two contests, respectively. In 2019, to measure and compare the scalability performance of the participating and other promising Query-by-Sketch or Query-by-Image 3D scene shape retrieval methods, we built a much larger extended benchmark for each type of retrieval which has thirty (30) classes and organized two extended tracks. Again, two and three different 3D scene shape retrieval methods have contended in these two tracks, separately. To solicit state-of-the-art approaches, we perform a comprehensive comparison of all the above methods and an additional new retrieval methods by evaluating them on the two benchmarks. The benchmarks, evaluation results and tools are publicly available at our track websites (Yuan et al., 2019 [1]; Abdul-Rashid et al., 2019 [2]; Yuan et al., 2019 [3]; Abdul-Rashid et al., 2019 [4]), while code for the evaluated methods are also available: http://github.com/3DSceneRetrieval.

Publication Title

Computer Vision and Image Understanding

Volume

201

Find in your library

Share

COinS