{"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/superpixel-hierarchy","title":"Superpixel Hierarchy","arxiv_id":"1605.06325","date":"2016-05-20","proceeding":null,"authors":["Xing Wei","Qingxiong Yang","Yihong Gong","Ming-Hsuan Yang","Narendra Ahuja"],"abstract":"Superpixel segmentation is becoming ubiquitous in computer vision. In\npractice, an object can either be represented by a number of segments in finer\nlevels of detail or included in a surrounding region at coarser levels of\ndetail, and thus a superpixel segmentation hierarchy is useful for applications\nthat require different levels of image segmentation detail depending on the\nparticular image objects segmented. Unfortunately, there is no method that can\ngenerate all scales of superpixels accurately in real-time. As a result, a\nsimple yet effective algorithm named Super Hierarchy (SH) is proposed in this\npaper. It is as accurate as the state-of-the-art but 1-2 orders of magnitude\nfaster. The proposed method can be directly integrated with recent efficient\nedge detectors like the structured forest edges to significantly outperforms\nthe state-of-the-art in terms of segmentation accuracy. Quantitative and\nqualitative evaluation on a number of computer vision applications was\nconducted, demonstrating that the proposed method is the top performer.","url_abs":"http://arxiv.org/abs/1605.06325v1","url_pdf":"http://arxiv.org/pdf/1605.06325v1.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":"superpixel-hierarchy","repo_url":"https://github.com/semiquark1/boruvka-superpixel","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"superpixels","task_name":"Superpixels"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}