File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Learning to Parse Wireframes in Images of Man-Made Environments

TitleLearning to Parse Wireframes in Images of Man-Made Environments
Authors
Issue Date2018
Citation
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2018, p. 626-635 How to Cite?
AbstractIn this paper, we propose a learning-based approach to the task of automatically extracting a 'wireframe' representation for images of cluttered man-made environments. The wireframe (see Fig. 1) contains all salient straight lines and their junctions of the scene that encode efficiently and accurately large-scale geometry and object shapes. To this end, we have built a very large new dataset of over 5,000 images with wireframes thoroughly labelled by humans. We have proposed two convolutional neural networks that are suitable for extracting junctions and lines with large spatial support, respectively. The networks trained on our dataset have achieved significantly better performance than state-of-the-art methods for junction detection and line segment detection, respectively. We have conducted extensive experiments to evaluate quantitatively and qualitatively the wireframes obtained by our method, and have convincingly shown that effectively and efficiently parsing wireframes for images of man-made environments is a feasible goal within reach. Such wireframes could benefit many important visual tasks such as feature correspondence, 3D reconstruction, vision-based mapping, localization, and navigation. The data and source code are available at https://github.com/huangkuns/wireframe.
Persistent Identifierhttp://hdl.handle.net/10722/327750
ISSN
2023 SCImago Journal Rankings: 10.331
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorHuang, Kun-
dc.contributor.authorWang, Yifan-
dc.contributor.authorZhou, Zihan-
dc.contributor.authorDing, Tianjiao-
dc.contributor.authorGao, Shenghua-
dc.contributor.authorMa, Yi-
dc.date.accessioned2023-05-08T02:26:33Z-
dc.date.available2023-05-08T02:26:33Z-
dc.date.issued2018-
dc.identifier.citationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2018, p. 626-635-
dc.identifier.issn1063-6919-
dc.identifier.urihttp://hdl.handle.net/10722/327750-
dc.description.abstractIn this paper, we propose a learning-based approach to the task of automatically extracting a 'wireframe' representation for images of cluttered man-made environments. The wireframe (see Fig. 1) contains all salient straight lines and their junctions of the scene that encode efficiently and accurately large-scale geometry and object shapes. To this end, we have built a very large new dataset of over 5,000 images with wireframes thoroughly labelled by humans. We have proposed two convolutional neural networks that are suitable for extracting junctions and lines with large spatial support, respectively. The networks trained on our dataset have achieved significantly better performance than state-of-the-art methods for junction detection and line segment detection, respectively. We have conducted extensive experiments to evaluate quantitatively and qualitatively the wireframes obtained by our method, and have convincingly shown that effectively and efficiently parsing wireframes for images of man-made environments is a feasible goal within reach. Such wireframes could benefit many important visual tasks such as feature correspondence, 3D reconstruction, vision-based mapping, localization, and navigation. The data and source code are available at https://github.com/huangkuns/wireframe.-
dc.languageeng-
dc.relation.ispartofProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition-
dc.titleLearning to Parse Wireframes in Images of Man-Made Environments-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/CVPR.2018.00072-
dc.identifier.scopuseid_2-s2.0-85062852479-
dc.identifier.spage626-
dc.identifier.epage635-
dc.identifier.isiWOS:000457843600065-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats