{"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/deep-convolutional-inverse-graphics-network","title":"Deep Convolutional Inverse Graphics Network","arxiv_id":"1503.03167","date":"2015-03-11","proceeding":"NeurIPS 2015 12","authors":["Tejas D. Kulkarni","Will Whitney","Pushmeet Kohli","Joshua B. Tenenbaum"],"abstract":"This paper presents the Deep Convolution Inverse Graphics Network (DC-IGN), a\nmodel that learns an interpretable representation of images. This\nrepresentation is disentangled with respect to transformations such as\nout-of-plane rotations and lighting variations. The DC-IGN model is composed of\nmultiple layers of convolution and de-convolution operators and is trained\nusing the Stochastic Gradient Variational Bayes (SGVB) algorithm. We propose a\ntraining procedure to encourage neurons in the graphics code layer to represent\na specific transformation (e.g. pose or light). Given a single input image, our\nmodel can generate new images of the same object with variations in pose and\nlighting. We present qualitative and quantitative results of the model's\nefficacy at learning a 3D rendering engine.","url_abs":"http://arxiv.org/abs/1503.03167v4","url_pdf":"http://arxiv.org/pdf/1503.03167v4.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":"deep-convolutional-inverse-graphics-network","repo_url":"https://github.com/DylanSpicker/STAT923-Final-Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"stochastic-gradient-variational-bayes","method_name":"Stochastic Gradient Variational Bayes"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1503.03167","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}