{"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/pointwise-convolutional-neural-networks","title":"Pointwise Convolutional Neural Networks","arxiv_id":"1712.05245","date":"2017-12-14","proceeding":"CVPR 2018 6","authors":["Binh-Son Hua","Minh-Khoi Tran","Sai-Kit Yeung"],"abstract":"Deep learning with 3D data such as reconstructed point clouds and CAD models\nhas received great research interests recently. However, the capability of\nusing point clouds with convolutional neural network has been so far not fully\nexplored. In this paper, we present a convolutional neural network for semantic\nsegmentation and object recognition with 3D point clouds. At the core of our\nnetwork is pointwise convolution, a new convolution operator that can be\napplied at each point of a point cloud. Our fully convolutional network design,\nwhile being surprisingly simple to implement, can yield competitive accuracy in\nboth semantic segmentation and object recognition task.","url_abs":"http://arxiv.org/abs/1712.05245v2","url_pdf":"http://arxiv.org/pdf/1712.05245v2.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":"pointwise-convolutional-neural-networks","repo_url":"https://github.com/hkust-vgd/pointwise","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"pointwise-convolutional-neural-networks","repo_url":"https://github.com/anshulpaigwar/pointwise-convolutional-neural-network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1712.05245","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}