{"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/semantic3dnet-a-new-large-scale-point-cloud","title":"Semantic3D.net: A new Large-scale Point Cloud Classification Benchmark","arxiv_id":"1704.03847","date":"2017-04-12","proceeding":null,"authors":["Timo Hackel","Nikolay Savinov","Lubor Ladicky","Jan D. Wegner","Konrad Schindler","Marc Pollefeys"],"abstract":"This paper presents a new 3D point cloud classification benchmark data set\nwith over four billion manually labelled points, meant as input for data-hungry\n(deep) learning methods. We also discuss first submissions to the benchmark\nthat use deep convolutional neural networks (CNNs) as a work horse, which\nalready show remarkable performance improvements over state-of-the-art. CNNs\nhave become the de-facto standard for many tasks in computer vision and machine\nlearning like semantic segmentation or object detection in images, but have no\nyet led to a true breakthrough for 3D point cloud labelling tasks due to lack\nof training data. With the massive data set presented in this paper, we aim at\nclosing this data gap to help unleash the full potential of deep learning\nmethods for 3D labelling tasks. Our semantic3D.net data set consists of dense\npoint clouds acquired with static terrestrial laser scanners. It contains 8\nsemantic classes and covers a wide range of urban outdoor scenes: churches,\nstreets, railroad tracks, squares, villages, soccer fields and castles. We\ndescribe our labelling interface and show that our data set provides more dense\nand complete point clouds with much higher overall number of labelled points\ncompared to those already available to the research community. We further\nprovide baseline method descriptions and comparison between methods submitted\nto our online system. We hope semantic3D.net will pave the way for deep\nlearning methods in 3D point cloud labelling to learn richer, more general 3D\nrepresentations, and first submissions after only a few months indicate that\nthis might indeed be the case.","url_abs":"http://arxiv.org/abs/1704.03847v1","url_pdf":"http://arxiv.org/pdf/1704.03847v1.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":"semantic3dnet-a-new-large-scale-point-cloud","repo_url":"https://github.com/nsavinov/semantic3dnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"torch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"3d-point-cloud-classification","task_name":"3D Point Cloud Classification"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"point-cloud-classification","task_name":"Point Cloud Classification"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[{"slug":"semantic3d","name":"Semantic3D","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.03847","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}