{"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/pointsift-a-sift-like-network-module-for-3d","title":"PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation","arxiv_id":"1807.00652","date":"2018-07-02","proceeding":null,"authors":["Mingyang Jiang","Yiran Wu","Tianqi Zhao","Zelin Zhao","Cewu Lu"],"abstract":"Recently, 3D understanding research sheds light on extracting features from\npoint cloud directly, which requires effective shape pattern description of\npoint clouds. Inspired by the outstanding 2D shape descriptor SIFT, we design a\nmodule called PointSIFT that encodes information of different orientations and\nis adaptive to scale of shape. Specifically, an orientation-encoding unit is\ndesigned to describe eight crucial orientations, and multi-scale representation\nis achieved by stacking several orientation-encoding units. PointSIFT module\ncan be integrated into various PointNet-based architecture to improve the\nrepresentation ability. Extensive experiments show our PointSIFT-based\nframework outperforms state-of-the-art method on standard benchmark datasets.\nThe code and trained model will be published accompanied by this paper.","url_abs":"http://arxiv.org/abs/1807.00652v2","url_pdf":"http://arxiv.org/pdf/1807.00652v2.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":"pointsift-a-sift-like-network-module-for-3d","repo_url":"https://github.com/583748495/psift","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"pointsift-a-sift-like-network-module-for-3d","repo_url":"https://github.com/LyapunovShao/pointSIFT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"pointsift-a-sift-like-network-module-for-3d","repo_url":"https://github.com/MVIG-SJTU/pointSIFT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"pointsift-a-sift-like-network-module-for-3d","repo_url":"https://github.com/Xiangxu-0103/Octant-CNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"point-cloud-segmentation","task_name":"Point Cloud Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.00652","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}