{"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/large-scale-point-cloud-semantic-segmentation","title":"Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs","arxiv_id":"1711.09869","date":"2017-11-27","proceeding":"CVPR 2018 6","authors":["Loic Landrieu","Martin Simonovsky"],"abstract":"We propose a novel deep learning-based framework to tackle the challenge of\nsemantic segmentation of large-scale point clouds of millions of points. We\nargue that the organization of 3D point clouds can be efficiently captured by a\nstructure called superpoint graph (SPG), derived from a partition of the\nscanned scene into geometrically homogeneous elements. SPGs offer a compact yet\nrich representation of contextual relationships between object parts, which is\nthen exploited by a graph convolutional network. Our framework sets a new state\nof the art for segmenting outdoor LiDAR scans (+11.9 and +8.8 mIoU points for\nboth Semantic3D test sets), as well as indoor scans (+12.4 mIoU points for the\nS3DIS dataset).","url_abs":"http://arxiv.org/abs/1711.09869v2","url_pdf":"http://arxiv.org/pdf/1711.09869v2.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":"large-scale-point-cloud-semantic-segmentation","repo_url":"https://github.com/loicland/superpoint_graph","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"large-scale-point-cloud-semantic-segmentation","repo_url":"https://github.com/jsgaobiao/superpoint_graph","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-semantic-segmentation-on-dales","task":"3D Semantic Segmentation","dataset":"DALES","model":"SPG","rank_in_archive_order":7,"of":9,"metrics":{"Model size":"280K","Overall Accuracy":"95.5","mIoU":"60.6"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-segmentation-on-semantickitti","task":"3D Semantic Segmentation","dataset":"SemanticKITTI","model":"SPGraph","rank_in_archive_order":40,"of":45,"metrics":{"test mIoU":"17.4%"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-segmentation-on-sensaturban","task":"3D Semantic Segmentation","dataset":"SensatUrban","model":"SPGraph","rank_in_archive_order":7,"of":8,"metrics":{"mIoU":"37.29"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-s3dis","task":"Semantic Segmentation","dataset":"S3DIS","model":"SPG","rank_in_archive_order":40,"of":54,"metrics":{"Mean IoU":"62.1","Number of params":"0.290M","Params (M)":"0.29","mAcc":"73","oAcc":"85.5"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-s3dis-area5","task":"Semantic Segmentation","dataset":"S3DIS Area5","model":"SPG","rank_in_archive_order":52,"of":61,"metrics":{"Number of params":"280K","mAcc":"66.5","mIoU":"58.04","oAcc":"86.38"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-semantic3d","task":"Semantic Segmentation","dataset":"Semantic3D","model":"SPG","rank_in_archive_order":5,"of":17,"metrics":{"mIoU":"76.2%","oAcc":"92.9%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-semantic3d","task":"Semantic Segmentation","dataset":"Semantic3D","model":"SPG","rank_in_archive_order":8,"of":17,"metrics":{"mIoU":"73.2%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.09869","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}