• Login
    View Item 
    •   Home
    • Research
    • Preprints
    • View Item
    •   Home
    • Research
    • Preprints
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of KAUSTCommunitiesIssue DateSubmit DateThis CollectionIssue DateSubmit Date

    My Account

    Login

    Quick Links

    Open Access PolicyORCID LibguidePlumX LibguideSubmit an Item

    Statistics

    Display statistics

    3D Instance Segmentation via Multi-Task Metric Learning

    • CSV
    • RefMan
    • EndNote
    • BibTex
    • RefWorks
    Thumbnail
    Name:
    Preprintfile1.pdf
    Size:
    5.440Mb
    Format:
    PDF
    Description:
    Pre-print
    Download
    Type
    Conference Paper
    Authors
    Lahoud, Jean
    Ghanem, Bernard cc
    Oswald, Martin R.
    Pollefeys, Marc
    KAUST Department
    Electrical Engineering Program
    Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
    Date
    2019
    Permanent link to this record
    http://hdl.handle.net/10754/660658
    
    Metadata
    Show full item record
    Abstract
    We propose a novel method for instance label segmentation of dense 3D voxel grids. We target volumetric scene representations, which have been acquired with depth sensors or multi-view stereo methods and which have been processed with semantic 3D reconstruction or scene completion methods. The main task is to learn shape information about individual object instances in order to accurately separate them, including connected and incompletely scanned objects. We solve the 3D instance-labeling problem with a multi-task learning strategy. The first goal is to learn an abstract feature embedding, which groups voxels with the same instance label close to each other while separating clusters with different instance labels from each other. The second goal is to learn instance information by densely estimating directional information of the instance's center of mass for each voxel. This is particularly useful to find instance boundaries in the clustering post-processing step, as well as, for scoring the segmentation quality for the first goal. Both synthetic and real-world experiments demonstrate the viability and merits of our approach. In fact, it achieves state-of-the-art performance on the ScanNet 3D instance segmentation benchmark.
    Citation
    Lahoud, J., Ghanem, B., Oswald, M. R., & Pollefeys, M. (2019). 3D Instance Segmentation via Multi-Task Metric Learning. 2019 IEEE/CVF International Conference on Computer Vision (ICCV). doi:10.1109/iccv.2019.00935
    Sponsors
    This research was supported by competitive funding from King Abdullah University of Science and Technology (KAUST). Further support was received by the Intelligence Advanced Research Projects Activity (IARPA) via Department of Interior/ Interior Business Center (DOI/IBC) contract number D17PC00280. The U.S. Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon. Disclaimer: The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of IARPA, DOI/IBC, or the U.S. Government.
    Publisher
    IEEE
    Conference/Event name
    2019 IEEE/CVF International Conference on Computer Vision (ICCV)
    DOI
    10.1109/ICCV.2019.00935
    arXiv
    1906.08650
    Additional Links
    https://ieeexplore.ieee.org/document/9008793/
    https://ieeexplore.ieee.org/document/9008793/
    https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9008793
    ae974a485f413a2113503eed53cd6c53
    10.1109/ICCV.2019.00935
    Scopus Count
    Collections
    Preprints; Electrical Engineering Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

    entitlement

     
    DSpace software copyright © 2002-2021  DuraSpace
    Quick Guide | Contact Us | Send Feedback
    Open Repository is a service hosted by 
    Atmire NV
     

    Export search results

    The export option will allow you to export the current search results of the entered query to a file. Different formats are available for download. To export the items, click on the button corresponding with the preferred download format.

    By default, clicking on the export buttons will result in a download of the allowed maximum amount of items. For anonymous users the allowed maximum amount is 50 search results.

    To select a subset of the search results, click "Selective Export" button and make a selection of the items you want to export. The amount of items that can be exported at once is similarly restricted as the full export.

    After making a selection, click one of the export format buttons. The amount of items that will be exported is indicated in the bubble next to export format.