{"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/inverting-face-embeddings-with-convolutional","title":"Inverting face embeddings with convolutional neural networks","arxiv_id":"1606.04189","date":"2016-06-14","proceeding":null,"authors":["Andrey Zhmoginov","Mark Sandler"],"abstract":"Deep neural networks have dramatically advanced the state of the art for many\nareas of machine learning. Recently they have been shown to have a remarkable\nability to generate highly complex visual artifacts such as images and text\nrather than simply recognize them.\n  In this work we use neural networks to effectively invert low-dimensional\nface embeddings while producing realistically looking consistent images. Our\ncontribution is twofold, first we show that a gradient ascent style approaches\ncan be used to reproduce consistent images, with a help of a guiding image.\nSecond, we demonstrate that we can train a separate neural network to\neffectively solve the minimization problem in one pass, and generate images in\nreal-time. We then evaluate the loss imposed by using a neural network instead\nof the gradient descent by comparing the final values of the minimized loss\nfunction.","url_abs":"http://arxiv.org/abs/1606.04189v2","url_pdf":"http://arxiv.org/pdf/1606.04189v2.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":"inverting-face-embeddings-with-convolutional","repo_url":"https://github.com/pavelgonchar/face-transfer-tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"face-transfer","task_name":"Face Transfer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1606.04189","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}