{"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/orientation-boosted-voxel-nets-for-3d-object","title":"Orientation-boosted Voxel Nets for 3D Object Recognition","arxiv_id":"1604.03351","date":"2016-04-12","proceeding":null,"authors":["Nima Sedaghat","Mohammadreza Zolfaghari","Ehsan Amiri","Thomas Brox"],"abstract":"Recent work has shown good recognition results in 3D object recognition using\n3D convolutional networks. In this paper, we show that the object orientation\nplays an important role in 3D recognition. More specifically, we argue that\nobjects induce different features in the network under rotation. Thus, we\napproach the category-level classification task as a multi-task problem, in\nwhich the network is trained to predict the pose of the object in addition to\nthe class label as a parallel task. We show that this yields significant\nimprovements in the classification results. We test our suggested architecture\non several datasets representing various 3D data sources: LiDAR data, CAD\nmodels, and RGB-D images. We report state-of-the-art results on classification\nas well as significant improvements in precision and speed over the baseline on\n3D detection.","url_abs":"http://arxiv.org/abs/1604.03351v2","url_pdf":"http://arxiv.org/pdf/1604.03351v2.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":[],"tasks":[{"task_slug":"3d-object-recognition","task_name":"3D Object Recognition"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-object-classification-on-modelnet10","task":"3D Object Classification","dataset":"ModelNet10","model":"ORION","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy":"93.8"},"uses_additional_data":false},{"leaderboard":"/sota/3d-point-cloud-classification-on-sydney-urban","task":"3D Point Cloud Classification","dataset":"Sydney Urban Objects","model":"ORION","rank_in_archive_order":2,"of":3,"metrics":{"F1":"77.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1604.03351","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}