{"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/recurrent-slice-networks-for-3d-segmentation","title":"Recurrent Slice Networks for 3D Segmentation of Point Clouds","arxiv_id":"1802.04402","date":"2018-02-13","proceeding":"CVPR 2018 6","authors":["Qiangui Huang","Weiyue Wang","Ulrich Neumann"],"abstract":"Point clouds are an efficient data format for 3D data. However, existing 3D\nsegmentation methods for point clouds either do not model local dependencies\n\\cite{pointnet} or require added computations \\cite{kd-net,pointnet2}. This\nwork presents a novel 3D segmentation framework, RSNet\\footnote{Codes are\nreleased here https://github.com/qianguih/RSNet}, to efficiently model local\nstructures in point clouds. The key component of the RSNet is a lightweight\nlocal dependency module. It is a combination of a novel slice pooling layer,\nRecurrent Neural Network (RNN) layers, and a slice unpooling layer. The slice\npooling layer is designed to project features of unordered points onto an\nordered sequence of feature vectors so that traditional end-to-end learning\nalgorithms (RNNs) can be applied. The performance of RSNet is validated by\ncomprehensive experiments on the S3DIS\\cite{stanford}, ScanNet\\cite{scannet},\nand ShapeNet \\cite{shapenet} datasets. In its simplest form, RSNets surpass all\nprevious state-of-the-art methods on these benchmarks. And comparisons against\nprevious state-of-the-art methods \\cite{pointnet, pointnet2} demonstrate the\nefficiency of RSNets.","url_abs":"http://arxiv.org/abs/1802.04402v2","url_pdf":"http://arxiv.org/pdf/1802.04402v2.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":"recurrent-slice-networks-for-3d-segmentation","repo_url":"https://github.com/qianguih/RSNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"recurrent-slice-networks-for-3d-segmentation","repo_url":"https://github.com/PatrickFeng/RPNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-s3dis","task":"Semantic Segmentation","dataset":"S3DIS","model":"RSNet","rank_in_archive_order":46,"of":54,"metrics":{"Mean IoU":"56.5","Number of params":"N/A","mAcc":"66.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.04402","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}