{"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-markov-random-field-for-image-modeling","title":"Deep Markov Random Field for Image Modeling","arxiv_id":"1609.02036","date":"2016-09-07","proceeding":null,"authors":["Zhirong Wu","Dahua Lin","Xiaoou Tang"],"abstract":"Markov Random Fields (MRFs), a formulation widely used in generative image\nmodeling, have long been plagued by the lack of expressive power. This issue is\nprimarily due to the fact that conventional MRFs formulations tend to use\nsimplistic factors to capture local patterns. In this paper, we move beyond\nsuch limitations, and propose a novel MRF model that uses fully-connected\nneurons to express the complex interactions among pixels. Through theoretical\nanalysis, we reveal an inherent connection between this model and recurrent\nneural networks, and thereon derive an approximated feed-forward network that\ncouples multiple RNNs along opposite directions. This formulation combines the\nexpressive power of deep neural networks and the cyclic dependency structure of\nMRF in a unified model, bringing the modeling capability to a new level. The\nfeed-forward approximation also allows it to be efficiently learned from data.\nExperimental results on a variety of low-level vision tasks show notable\nimprovement over state-of-the-arts.","url_abs":"http://arxiv.org/abs/1609.02036v1","url_pdf":"http://arxiv.org/pdf/1609.02036v1.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-markov-random-field-for-image-modeling","repo_url":"https://github.com/zhirongw/deep-mrf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}