BIROn - Birkbeck Institutional Research Online

    Bridging composite and real: towards end-to-end deep image matting

    Li, J. and Zhang, J. and Maybank, Stephen (2021) Bridging composite and real: towards end-to-end deep image matting. International Journal of Computer Vision , ISSN 0920-5691. (In Press)

    [img] Text
    BridgingCompositeAndReal.pdf - Author's Accepted Manuscript
    Restricted to Repository staff only

    Download (8MB) | Request a copy

    Abstract

    Extracting accurate foregrounds from natural images benefits many downstream applications such as film production and augmented reality. However, the furry characteristics and various appearance of the foregrounds, e.g., animal and portrait, challenge existing matting methods, which usually require extra user inputs such as trimap or scribbles. To resolve these problems, we study the distinct roles of semantics and details for image matting and decompose the task into two parallel sub-tasks: high-level semantic segmentation and low-level details matting. Specifically, we propose a novel glance and Focus Matting network (GFM), which employs a shared encoder and two separate decoders to learn both tasks in a collaborative manner for end-to-end natural image matting. Besides, due to the limitation of available natural images in the matting task, previous methods typically adopt composite images for training and evaluation, which result in limited generalization ability on real-world images. In this paper, we investigate the domain gap issue between composite images and real-world images systematically by conducting comprehensive analyses of various discrepancies between the foreground and background images. We find that a carefully desinged composition route RSSN that aims to reduce the discepancies can lead to a better model with remarkable generalization ability . Furthermore, we provide a bench mark containing 2,000 high-resolution real-world animal images and 10,000 portrait images along with their manually labelled alpha mattes to serve as a test bed for evaluating matting model's generalization ability on real-world images. Comprehensive empirical studies have demonstrated that GFM outperforms state-of-the-art methods and effectively reduces the generalization error. The code and the datasets will be released at https://github.com/JizhiziLi/GFM.

    Metadata

    Item Type: Article
    Keyword(s) / Subject(s): Image Matting, Deep Learning, Alpha matte, Image Composition, Domain Gap
    School: School of Business, Economics & Informatics > Computer Science and Information Systems
    Depositing User: Steve Maybank
    Date Deposited: 15 Nov 2021 12:01
    Last Modified: 04 Jul 2022 12:46
    URI: https://eprints.bbk.ac.uk/id/eprint/46501

    Statistics

    Activity Overview
    6 month trend
    1Download
    6 month trend
    38Hits

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item Edit/View Item