Extended 2D Scene Sketch-Based 3D Scene Retrieval

dc.contributor.authorYuan, Juefeien_US
dc.contributor.authorAbdul-Rashid, Hameeden_US
dc.contributor.authorLi, Boen_US
dc.contributor.authorLu, Yijuanen_US
dc.contributor.authorSchreck, Tobiasen_US
dc.contributor.authorBui, Ngoc-Minhen_US
dc.contributor.authorDo, Trong-Leen_US
dc.contributor.authorNguyen, Khac-Tuanen_US
dc.contributor.authorNguyen, Thanh-Anen_US
dc.contributor.authorNguyen, Vinh-Tiepen_US
dc.contributor.authorTran, Minh-Trieten_US
dc.contributor.authorWang, Tianyangen_US
dc.contributor.editorBiasotti, Silvia and Lavoué, Guillaume and Veltkamp, Remcoen_US
dc.date.accessioned2019-05-04T14:06:00Z
dc.date.available2019-05-04T14:06:00Z
dc.date.issued2019
dc.description.abstractSketch-based 3D scene retrieval is to retrieve 3D scene models given a user's hand-drawn 2D scene sketch. It is a brand new but also very challenging research topic in the field of 3D object retrieval due to the semantic gap in their representations: 3D scene models or views differ from non-realistic 2D scene sketches. To boost this interesting research, we organized a 2D Scene Sketch-Based 3D Scene Retrieval track in SHREC'18, resulting a SceneSBR18 benchmark which contains 10 scene classes. In order to make it more comprehensive, we have extended the number of the scene categories from the initial 10 classes in the SceneSBR2018 benchmark to 30 classes, resulting in a new and more challenging benchmark SceneSBR2019 which has 750 2D scene sketches and 3,000 3D scene models. Therefore, the objective of this track is to further evaluate the performance and scalability of different 2D scene sketch-based 3D scene model retrieval algorithms using this extended and more comprehensive new benchmark. In this track, two groups from USA and Vietnam have successfully submitted 4 runs. Based on 7 commonly used retrieval metrics, we evaluate their retrieval performance. We have also conducted a comprehensive analysis and discussion of these methods and proposed several future research directions to deal with this challenging research topic. Deep learning techniques have been proved their great potentials again in dealing with this challenging retrieval task, in terms of both retrieval accuracy and scalability to a larger dataset. We hope this publicly available benchmark, together with its evaluation results and source code, will further enrich and promote 2D scene sketch-based 3D scene retrieval research area and its corresponding applications.en_US
dc.description.sectionheadersSHREC Session 1
dc.description.seriesinformationEurographics Workshop on 3D Object Retrieval
dc.identifier.doi10.2312/3dor.20191059
dc.identifier.isbn978-3-03868-077-2
dc.identifier.issn1997-0471
dc.identifier.pages33-39
dc.identifier.urihttps://doi.org/10.2312/3dor.20191059
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/3dor20191059
dc.publisherThe Eurographics Associationen_US
dc.subjectH.3.3 [Computer Graphics]
dc.subjectInformation Systems
dc.subjectInformation Search and Retrieval
dc.titleExtended 2D Scene Sketch-Based 3D Scene Retrievalen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
033-039.pdf
Size:
808.57 KB
Format:
Adobe Portable Document Format
Collections