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.
|Number of pages||9|
|Publication status||Published - Feb 2019|
|Event||33rd AAAI Conference on Artificial Intelligence, AAAI 2019 - Hilton Hawaiian Village, Honolulu, United States|
Duration: 27 Jan 2019 → 1 Feb 2019
Conference number: 33
|Conference||33rd AAAI Conference on Artificial Intelligence, AAAI 2019|
|Period||27/01/19 → 1/02/19|