{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-layer-based-sequential-framework-for-scene","title":"A Layer-Based Sequential Framework for Scene Generation with GANs","arxiv_id":"1902.00671","date":"2019-02-02","proceeding":null,"authors":["Mehmet Ozgur Turkoglu","William Thong","Luuk Spreeuwers","Berkay Kicanaoglu"],"abstract":"The visual world we sense, interpret and interact everyday is a complex\ncomposition of interleaved physical entities. Therefore, it is a very\nchallenging task to generate vivid scenes of similar complexity using\ncomputers. In this work, we present a scene generation framework based on\nGenerative Adversarial Networks (GANs) to sequentially compose a scene,\nbreaking down the underlying problem into smaller ones. Different than the\nexisting approaches, our framework offers an explicit control over the elements\nof a scene through separate background and foreground generators. Starting with\nan initially generated background, foreground objects then populate the scene\none-by-one in a sequential manner. Via quantitative and qualitative experiments\non a subset of the MS-COCO dataset, we show that our proposed framework\nproduces not only more diverse images but also copes better with affine\ntransformations and occlusion artifacts of foreground objects than its\ncounterparts.","url_abs":"http://arxiv.org/abs/1902.00671v1","url_pdf":"http://arxiv.org/pdf/1902.00671v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-layer-based-sequential-framework-for-scene","repo_url":"https://github.com/0zgur0/Seq_Scene_Gen","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"conditional-image-generation","task_name":"Conditional Image Generation"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"scene-generation","task_name":"Scene Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.00671","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}