{"status":"public","article_processing_charge":"No","day":"01","publication_status":"submitted","main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/2004.00642"}],"department":[{"_id":"ChLa"}],"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","month":"04","date_updated":"2021-01-12T08:16:44Z","publication":"arXiv","title":"Object-centric image generation with factored depths, locations, and appearances","date_created":"2020-06-29T23:55:23Z","oa":1,"article_number":"2004.00642","language":[{"iso":"eng"}],"type":"preprint","license":"https://creativecommons.org/licenses/by-sa/4.0/","_id":"8063","external_id":{"arxiv":["2004.00642"]},"citation":{"apa":"Anciukevicius, T., Lampert, C., &#38; Henderson, P. M. (n.d.). Object-centric image generation with factored depths, locations, and appearances. <i>arXiv</i>.","chicago":"Anciukevicius, Titas, Christoph Lampert, and Paul M Henderson. “Object-Centric Image Generation with Factored Depths, Locations, and Appearances.” <i>ArXiv</i>, n.d.","ieee":"T. Anciukevicius, C. Lampert, and P. M. Henderson, “Object-centric image generation with factored depths, locations, and appearances,” <i>arXiv</i>. .","ista":"Anciukevicius T, Lampert C, Henderson PM. Object-centric image generation with factored depths, locations, and appearances. arXiv, 2004.00642.","ama":"Anciukevicius T, Lampert C, Henderson PM. Object-centric image generation with factored depths, locations, and appearances. <i>arXiv</i>.","mla":"Anciukevicius, Titas, et al. “Object-Centric Image Generation with Factored Depths, Locations, and Appearances.” <i>ArXiv</i>, 2004.00642.","short":"T. Anciukevicius, C. Lampert, P.M. Henderson, ArXiv (n.d.)."},"abstract":[{"lang":"eng","text":"We present a generative model of images that explicitly reasons over the set\r\nof objects they show. Our model learns a structured latent representation that\r\nseparates objects from each other and from the background; unlike prior works,\r\nit explicitly represents the 2D position and depth of each object, as well as\r\nan embedding of its segmentation mask and appearance. The model can be trained\r\nfrom images alone in a purely unsupervised fashion without the need for object\r\nmasks or depth information. Moreover, it always generates complete objects,\r\neven though a significant fraction of training images contain occlusions.\r\nFinally, we show that our model can infer decompositions of novel images into\r\ntheir constituent objects, including accurate prediction of depth ordering and\r\nsegmentation of occluded parts."}],"author":[{"first_name":"Titas","last_name":"Anciukevicius","full_name":"Anciukevicius, Titas"},{"full_name":"Lampert, Christoph","last_name":"Lampert","first_name":"Christoph","orcid":"0000-0001-8622-7887","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87"},{"first_name":"Paul M","full_name":"Henderson, Paul M","last_name":"Henderson","id":"13C09E74-18D9-11E9-8878-32CFE5697425","orcid":"0000-0002-5198-7445"}],"date_published":"2020-04-01T00:00:00Z","tmp":{"image":"/images/cc_by_sa.png","short":"CC BY-SA (4.0)","legal_code_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","name":"Creative Commons Attribution-ShareAlike 4.0 International Public License (CC BY-SA 4.0)"},"oa_version":"Preprint","year":"2020","ddc":["004"]}