{"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/a-benchmark-for-edge-preserving-image","title":"A Benchmark for Edge-Preserving Image Smoothing","arxiv_id":"1904.01579","date":"2019-04-02","proceeding":null,"authors":["Feida Zhu","Zhetong Liang","Xixi Jia","Lei Zhang","Yizhou Yu"],"abstract":"Edge-preserving image smoothing is an important step for many low-level\nvision problems. Though many algorithms have been proposed, there are several\ndifficulties hindering its further development. First, most existing algorithms\ncannot perform well on a wide range of image contents using a single parameter\nsetting. Second, the performance evaluation of edge-preserving image smoothing\nremains subjective, and there lacks a widely accepted datasets to objectively\ncompare the different algorithms. To address these issues and further advance\nthe state of the art, in this work we propose a benchmark for edge-preserving\nimage smoothing. This benchmark includes an image dataset with groundtruth\nimage smoothing results as well as baseline algorithms that can generate\ncompetitive edge-preserving smoothing results for a wide range of image\ncontents. The established dataset contains 500 training and testing images with\na number of representative visual object categories, while the baseline methods\nin our benchmark are built upon representative deep convolutional network\narchitectures, on top of which we design novel loss functions well suited for\nedge-preserving image smoothing. The trained deep networks run faster than most\nstate-of-the-art smoothing algorithms with leading smoothing results both\nqualitatively and quantitatively. The benchmark is publicly accessible via\nhttps://github.com/zhufeida/Benchmark_EPS.","url_abs":"http://arxiv.org/abs/1904.01579v1","url_pdf":"http://arxiv.org/pdf/1904.01579v1.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":"a-benchmark-for-edge-preserving-image","repo_url":"https://github.com/zhufeida/Benchmark_EPS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"image-smoothing","task_name":"image smoothing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.01579","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}