{"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/escape-from-cells-deep-kd-networks-for-the","title":"Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models","arxiv_id":"1704.01222","date":"2017-04-04","proceeding":"ICCV 2017 10","authors":["Roman Klokov","Victor Lempitsky"],"abstract":"We present a new deep learning architecture (called Kd-network) that is\ndesigned for 3D model recognition tasks and works with unstructured point\nclouds. The new architecture performs multiplicative transformations and share\nparameters of these transformations according to the subdivisions of the point\nclouds imposed onto them by Kd-trees. Unlike the currently dominant\nconvolutional architectures that usually require rasterization on uniform\ntwo-dimensional or three-dimensional grids, Kd-networks do not rely on such\ngrids in any way and therefore avoid poor scaling behaviour. In a series of\nexperiments with popular shape recognition benchmarks, Kd-networks demonstrate\ncompetitive performance in a number of shape recognition tasks such as shape\nclassification, shape retrieval and shape part segmentation.","url_abs":"http://arxiv.org/abs/1704.01222v2","url_pdf":"http://arxiv.org/pdf/1704.01222v2.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":"escape-from-cells-deep-kd-networks-for-the","repo_url":"https://github.com/fxia22/kdnet.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"escape-from-cells-deep-kd-networks-for-the","repo_url":"https://github.com/qq456cvb/KdNet-Tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"3d-part-segmentation","task_name":"3D Part Segmentation"},{"task_slug":"3d-point-cloud-classification","task_name":"3D Point Cloud Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-part-segmentation-on-shapenet-part","task":"3D Part Segmentation","dataset":"ShapeNet-Part","model":"Kd-net","rank_in_archive_order":64,"of":67,"metrics":{"Class Average IoU":"77.4","Instance Average IoU":"82.3"},"uses_additional_data":false},{"leaderboard":"/sota/3d-point-cloud-classification-on-modelnet40","task":"3D Point Cloud Classification","dataset":"ModelNet40","model":"Kd-Net","rank_in_archive_order":96,"of":111,"metrics":{"Overall Accuracy":"91.8"},"uses_additional_data":false},{"leaderboard":"/sota/3d-point-cloud-classification-on-modelnet40","task":"3D Point Cloud Classification","dataset":"ModelNet40","model":"Kd-net","rank_in_archive_order":102,"of":111,"metrics":{"Overall Accuracy":"90.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.01222","atlas_url":"https://app.syntology.ai/?focus=1704.01222","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}