{"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/deep-sliding-shapes-for-amodal-3d-object","title":"Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images","arxiv_id":"1511.02300","date":"2015-11-07","proceeding":"CVPR 2016 6","authors":["Shuran Song","Jianxiong Xiao"],"abstract":"We focus on the task of amodal 3D object detection in RGB-D images, which\naims to produce a 3D bounding box of an object in metric form at its full\nextent. We introduce Deep Sliding Shapes, a 3D ConvNet formulation that takes a\n3D volumetric scene from a RGB-D image as input and outputs 3D object bounding\nboxes. In our approach, we propose the first 3D Region Proposal Network (RPN)\nto learn objectness from geometric shapes and the first joint Object\nRecognition Network (ORN) to extract geometric features in 3D and color\nfeatures in 2D. In particular, we handle objects of various sizes by training\nan amodal RPN at two different scales and an ORN to regress 3D bounding boxes.\nExperiments show that our algorithm outperforms the state-of-the-art by 13.8 in\nmAP and is 200x faster than the original Sliding Shapes. All source code and\npre-trained models will be available at GitHub.","url_abs":"http://arxiv.org/abs/1511.02300v2","url_pdf":"http://arxiv.org/pdf/1511.02300v2.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-detection","task_name":"3D Object Detection"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"region-proposal","task_name":"Region Proposal"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"rpn","method_name":"RPN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-object-detection-on-sun-rgbd-val","task":"3D Object Detection","dataset":"SUN-RGBD val","model":"DSS","rank_in_archive_order":32,"of":32,"metrics":{"Inference Speed (s)":"19.55"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1511.02300","atlas_url":"https://app.syntology.ai/?focus=1511.02300","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}