{"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/image-smoothing-via-unsupervised-learning","title":"Image Smoothing via Unsupervised Learning","arxiv_id":"1811.02804","date":"2018-11-07","proceeding":null,"authors":["Qingnan Fan","Jiaolong Yang","David Wipf","Baoquan Chen","Xin Tong"],"abstract":"Image smoothing represents a fundamental component of many disparate computer\nvision and graphics applications. In this paper, we present a unified\nunsupervised (label-free) learning framework that facilitates generating\nflexible and high-quality smoothing effects by directly learning from data\nusing deep convolutional neural networks (CNNs). The heart of the design is the\ntraining signal as a novel energy function that includes an edge-preserving\nregularizer which helps maintain important yet potentially vulnerable image\nstructures, and a spatially-adaptive Lp flattening criterion which imposes\ndifferent forms of regularization onto different image regions for better\nsmoothing quality. We implement a diverse set of image smoothing solutions\nemploying the unified framework targeting various applications such as, image\nabstraction, pencil sketching, detail enhancement, texture removal and\ncontent-aware image manipulation, and obtain results comparable with or better\nthan previous methods. Moreover, our method is extremely fast with a modern GPU\n(e.g, 200 fps for 1280x720 images). Our codes and model are released in\nhttps://github.com/fqnchina/ImageSmoothing.","url_abs":"http://arxiv.org/abs/1811.02804v1","url_pdf":"http://arxiv.org/pdf/1811.02804v1.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":"image-smoothing-via-unsupervised-learning","repo_url":"https://github.com/fqnchina/ImageSmoothing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"image-manipulation","task_name":"Image Manipulation"},{"task_slug":"image-smoothing","task_name":"image smoothing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.02804","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}