{"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/planercnn-3d-plane-detection-and","title":"PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image","arxiv_id":"1812.04072","date":"2018-12-10","proceeding":"CVPR 2019 6","authors":["Chen Liu","Kihwan Kim","Jinwei Gu","Yasutaka Furukawa","Jan Kautz"],"abstract":"This paper proposes a deep neural architecture, PlaneRCNN, that detects and\nreconstructs piecewise planar surfaces from a single RGB image. PlaneRCNN\nemploys a variant of Mask R-CNN to detect planes with their plane parameters\nand segmentation masks. PlaneRCNN then jointly refines all the segmentation\nmasks with a novel loss enforcing the consistency with a nearby view during\ntraining. The paper also presents a new benchmark with more fine-grained plane\nsegmentations in the ground-truth, in which, PlaneRCNN outperforms existing\nstate-of-the-art methods with significant margins in the plane detection,\nsegmentation, and reconstruction metrics. PlaneRCNN makes an important step\ntowards robust plane extraction, which would have an immediate impact on a wide\nrange of applications including Robotics, Augmented Reality, and Virtual\nReality.","url_abs":"http://arxiv.org/abs/1812.04072v2","url_pdf":"http://arxiv.org/pdf/1812.04072v2.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":"planercnn-3d-plane-detection-and","repo_url":"https://github.com/NVlabs/planercnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"planercnn-3d-plane-detection-and","repo_url":"https://github.com/a-nau/Plane-Segmentation-Refinement","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"3d-plane-detection","task_name":"3D Plane Detection"},{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"mask-r-cnn","method_name":"Mask R-CNN"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roi-align","method_name":"RoIAlign"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.04072","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}