{"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/auto-encoding-progressive-generative","title":"Auto-Encoding Progressive Generative Adversarial Networks For 3D Multi Object Scenes","arxiv_id":"1903.03477","date":"2019-03-08","proceeding":null,"authors":["Vedant Singh","Manan Oza","Himanshu Vaghela","Pratik Kanani"],"abstract":"3D multi object generative models allow us to synthesize a large range of\nnovel 3D multi object scenes and also identify objects, shapes, layouts and\ntheir positions. But multi object scenes are difficult to create because of the\ndataset being multimodal in nature. The conventional 3D generative adversarial\nmodels are not efficient in generating multi object scenes, they usually tend\nto generate either one object or generate fuzzy results of multiple objects.\nAuto-encoder models have much scope in feature extraction and representation\nlearning using the unsupervised paradigm in probabilistic spaces. We try to\nmake use of this property in our proposed model. In this paper we propose a\nnovel architecture using 3DConvNets trained with the progressive training\nparadigm that has been able to generate realistic high resolution 3D scenes of\nrooms, bedrooms, offices etc. with various pieces of furniture and objects. We\nmake use of the adversarial auto-encoder along with the WGAN-GP loss parameter\nin our discriminator loss function. Finally this new approach to multi object\nscene generation has also been able to generate more number of objects per\nscene.","url_abs":"http://arxiv.org/abs/1903.03477v1","url_pdf":"http://arxiv.org/pdf/1903.03477v1.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":"auto-encoding-progressive-generative","repo_url":"https://github.com/yunishi3/3D-FCR-alphaGAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"scene-generation","task_name":"Scene Generation"}],"methods":[{"method_slug":"wgan-gp-loss","method_name":"WGAN-GP Loss"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}