A Layer-Based Sequential Framework for Scene Generation with GANs

Mehmet Ozgur Turkoglu, Luuk Spreeuwers, William Thong, Berkay Kicanaoglu

    Research output: Contribution to conferencePaperAcademicpeer-review

    2 Citations (Scopus)
    2 Downloads (Pure)

    Abstract

    The visual world we sense, interpret and interact everyday is a complex composition of interleaved physical entities. Therefore, it is a very challenging task to generate vivid scenes of similar complexity using computers. In this work, we present a scene generation framework based on Generative Adversarial Networks (GANs) to sequentially compose a scene, breaking down the underlying problem into smaller ones. Different than the existing approaches, our framework offers an explicit control over the elements of a scene through separate background and foreground generators. Starting with an initially generated background, foreground objects then populate the scene one-by-one in a sequential manner. Via quantitative and qualitative experiments on a subset of the MS-COCO dataset, we show that our proposed framework produces not only more diverse images but also copes better with affine transformations and occlusion artifacts of foreground objects than its counterparts.
    Original languageEnglish
    Number of pages9
    Publication statusPublished - Feb 2019
    Event33rd AAAI Conference on Artificial Intelligence, AAAI 2019 - Hilton Hawaiian Village, Honolulu, United States
    Duration: 27 Jan 20191 Feb 2019
    Conference number: 33
    https://aaai.org/Conferences/AAAI-19/

    Conference

    Conference33rd AAAI Conference on Artificial Intelligence, AAAI 2019
    Abbreviated titleAAAI-19
    CountryUnited States
    CityHonolulu
    Period27/01/191/02/19
    Internet address

    Fingerprint Dive into the research topics of 'A Layer-Based Sequential Framework for Scene Generation with GANs'. Together they form a unique fingerprint.

    Cite this