{"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/seeds-superpixels-extracted-via-energy-driven","title":"SEEDS: Superpixels Extracted via Energy-Driven Sampling","arxiv_id":"1309.3848","date":"2013-09-16","proceeding":null,"authors":["Michael Van den Bergh","Xavier Boix","Gemma Roig","Luc van Gool"],"abstract":"Superpixel algorithms aim to over-segment the image by grouping pixels that\nbelong to the same object. Many state-of-the-art superpixel algorithms rely on\nminimizing objective functions to enforce color ho- mogeneity. The optimization\nis accomplished by sophis- ticated methods that progressively build the\nsuperpix- els, typically by adding cuts or growing superpixels. As a result,\nthey are computationally too expensive for real-time applications. We introduce\na new approach based on a simple hill-climbing optimization. Starting from an\ninitial superpixel partitioning, it continuously refines the superpixels by\nmodifying the boundaries. We define a robust and fast to evaluate energy\nfunction, based on enforcing color similarity between the bound- aries and the\nsuperpixel color histogram. In a series of experiments, we show that we achieve\nan excellent com- promise between accuracy and efficiency. We are able to\nachieve a performance comparable to the state-of- the-art, but in real-time on\na single Intel i7 CPU at 2.8GHz.","url_abs":"http://arxiv.org/abs/1309.3848v1","url_pdf":"http://arxiv.org/pdf/1309.3848v1.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":"seeds-superpixels-extracted-via-energy-driven","repo_url":"https://github.com/davidstutz/superpixel-benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":"superpixels","task_name":"Superpixels"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1309.3848","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}