{"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/iterative-deep-learning-for-road-topology","title":"Iterative Deep Learning for Road Topology Extraction","arxiv_id":"1808.09814","date":"2018-08-28","proceeding":null,"authors":["Carles Ventura","Jordi Pont-Tuset","Sergi Caelles","Kevis-Kokitsi Maninis","Luc van Gool"],"abstract":"This paper tackles the task of estimating the topology of road networks from\naerial images. Building on top of a global model that performs a dense\nsemantical classification of the pixels of the image, we design a Convolutional\nNeural Network (CNN) that predicts the local connectivity among the central\npixel of an input patch and its border points. By iterating this local\nconnectivity we sweep the whole image and infer the global topology of the road\nnetwork, inspired by a human delineating a complex network with the tip of\ntheir finger. We perform an extensive and comprehensive qualitative and\nquantitative evaluation on the road network estimation task, and show that our\nmethod also generalizes well when moving to networks of retinal vessels.","url_abs":"http://arxiv.org/abs/1808.09814v1","url_pdf":"http://arxiv.org/pdf/1808.09814v1.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":"iterative-deep-learning-for-road-topology","repo_url":"https://github.com/carlesventura/iterative-deep-learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.09814","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}