{"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/exploring-the-neural-algorithm-of-artistic","title":"Exploring the Neural Algorithm of Artistic Style","arxiv_id":"1602.07188","date":"2016-02-23","proceeding":null,"authors":["Yaroslav Nikulin","Roman Novak"],"abstract":"We explore the method of style transfer presented in the article \"A Neural\nAlgorithm of Artistic Style\" by Leon A. Gatys, Alexander S. Ecker and Matthias\nBethge (arXiv:1508.06576).\n  We first demonstrate the power of the suggested style space on a few\nexamples. We then vary different hyper-parameters and program properties that\nwere not discussed in the original paper, among which are the recognition\nnetwork used, starting point of the gradient descent and different ways to\npartition style and content layers. We also give a brief comparison of some of\nthe existing algorithm implementations and deep learning frameworks used.\n  To study the style space further we attempt to generate synthetic images by\nmaximizing a single entry in one of the Gram matrices $\\mathcal{G}_l$ and some\ninteresting results are observed. Next, we try to mimic the sparsity and\nintensity distribution of Gram matrices obtained from a real painting and\ngenerate more complex textures.\n  Finally, we propose two new style representations built on top of network's\nfeatures and discuss how one could be used to achieve local and potentially\ncontent-aware style transfer.","url_abs":"http://arxiv.org/abs/1602.07188v2","url_pdf":"http://arxiv.org/pdf/1602.07188v2.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":"exploring-the-neural-algorithm-of-artistic","repo_url":"https://github.com/gordicaleksa/pytorch-neural-style-transfer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"style-transfer","task_name":"Style Transfer"}],"methods":[],"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}