[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-513627-105":59,"doc-detail-513627-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","planercnn-3d-plane-detection-and-reconstruction-from-a-single-image-513627","PlaneRCNN - 3D Plane Detection and Reconstruction from a Single Image","","PlaneRCNN presents a deep neural architecture for detecting planar regions and reconstructing piecewise planar depthmaps from a single RGB image. The method applies a Mask R-CNN variant to predict plane parameters and per-instance segmentation masks, then refines all masks jointly using a consistency loss with a nearby view during training. PlaneRCNN also introduces a new benchmark with finer ground-truth plane segmentations, yielding substantial improvements in plane detection, segmentation, and reconstruction metrics across tasks and scenes.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/planercnn-3d-plane-detection-and-reconstruction-from-a-single-image-513627/513627/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/planercnn-3d-plane-detection-and-reconstruction-from-a-single-image-513627/513627.png","ImageObject",300,407,{"name":92,"@type":93},"Guten tag","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-16","2026-10-06",true,{"@type":102,"interactionType":103,"userInteractionCount":52},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does PlaneRCNN address?","Question",{"text":112,"@type":113},"PlaneRCNN addresses inference of piecewise planar structure from a single RGB image, including detecting planes and reconstructing a piecewise planar depthmap.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does PlaneRCNN detect planes?",{"text":117,"@type":113},"PlaneRCNN uses a Mask R-CNN variant to detect planar regions and predict plane parameters along with instance segmentation masks and per-pixel depth values.",{"name":119,"@type":110,"acceptedAnswer":120},"How does PlaneRCNN improve segmentation during training?",{"text":121,"@type":113},"It refines all segmentation masks jointly using a novel loss that enforces consistency with a nearby view during training.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},513627,1791384977,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":52,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":52,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":144,"preview_page_count":19,"preview_urls":145},687212321768,"https://ap-avatar.wpscdn.com/avatar/a0010bdbe886d2fe77?x-image-process=image/resize,m_fixed,w_180,h_180&k=1789897067658708522","PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image  \nChen Liu 1 ;2 􀀃 Kihwan Kim 1 Jinwei Gu 1 ;3 􀀃 Yasutaka Furukawa4 Jan Kautz 1  \n1NVIDIA 2Washington University in St. Louis  \n3 SenseTime 4 Simon Fraser University  \nFigure 1 . This paper proposes a deep neural architecture, PlaneRCNN, that detects planar regions and reconstructs a piecewise planar depthmap from a single RGB image. From left to right, an input image, segmented planar regions, estimated depthmap, and reconstructed planar surfaces.  \nAbstract  \nThis paper proposes a deep neural architecture, PlaneRCNN, that detects and reconstructs piecewise planar surfaces from a single RGB image. PlaneRCNN employs a variant of Mask R-CNN to detect planes with their plane parameters and segmentation masks. PlaneRCNN then jointly reﬁnes all the segmentation masks with a novel loss enforcing the consistency with a nearby view during training. The paper also presents a new benchmark with more ﬁne-grained plane segmentations in the ground-truth, in which, PlaneRCNN outperforms existing state-of-theart methods with signiﬁcant margins in the plane detection, segmentation, and reconstruction metrics. PlaneRCNN makes an important step towards robust plane extraction, which would have an immediate impact on a wide range of applications including Robotics, Augmented Reality, and Virtual Reality. Code and data are available at [https://research.nvidia.com/publication/2019-06](https://research.nvidia.com/publication/2019-06 PlaneRCNN)[ ](https://research.nvidia.com/publication/2019-06 PlaneRCNN)[PlaneRCNN](https://research.nvidia.com/publication/2019-06 PlaneRCNN).  \n1. Introduction  \nPlanar regions in 3D scenes offer important geometric cues in a variety of 3D perception tasks such as scene understanding [42], scene reconstruction [3], and robot navigation [18, 56] . Accordingly, piecewise planar scene reconstruction has been a focus of computer vision research  \n􀀃 The authors contributed to this work when they were at NVIDIA.  \nfor many years, for example, plausible recovery of planar structures from a single image [16], volumetric piecewise planar reconstruction from point clouds [3], and Manhattan depthmap reconstruction from multiple images [11] .  \nA difﬁcult yet fundamental task is the inference of apiecewise planar structure from a single RGB image, posing two key challenges. First, 3D plane reconstruction from a single image is an ill-posed problem, requiring rich scene priors. Second, planar structures abundant in man-made environments often lack textures, requiring global image understanding as opposed to local texture analysis. Recently, PlaneNet [27] and PlaneRecover [49] made a breakthrough by introducing the use of Convolutional Neural Networks (CNNs) and formulating the problem as a plane segmentation task. While generating promising results, they suffer from three major limitations: 1) Missing small surfaces; 2) Requiring the maximum number of planes in a single image a priori; and 3) Poor generalization across domains (e.g., trained for indoors images and tested outdoors) .  \nThis paper proposes a novel deep neural architecture, PlaneRCNN, that addresses these issues and more effectively infers piecewise planar structure from a single RGB image (Fig. 1) . PlaneRCNN consists of three components.  \nThe ﬁrst component is a plane detection network built upon Mask R-CNN [14] . Besides an instance mask for each planar region, we also estimate the plane normal and perpixel depth values. With known camera intrinsics, we can further reconstruct the 3D planes from the detected planar regions. This detection framework is more ﬂexible and can  \nhandle an arbitrary number of planar regions in an image. To the best of our knowledge, this paper is the ﬁrst to introduce a detection network, common in object recognition, to the depthmap reconstruction task. The second component is a segmentation reﬁnement network that jointly optimizes extracted segmentation masks to mo","cbCaiuOXAnUtYMPq","https://ap.wps.com/l/cbCaiuOXAnUtYMPq","pdf",8111863,"English","# Introduction\n## Motivation and key challenges\n## Proposed approach overview\n# Related Work","[{\"question\":\"What problem does PlaneRCNN address?\",\"answer\":\"PlaneRCNN addresses inference of piecewise planar structure from a single RGB image, including detecting planes and reconstructing a piecewise planar depthmap.\"},{\"question\":\"How does PlaneRCNN detect planes?\",\"answer\":\"PlaneRCNN uses a Mask R-CNN variant to detect planar regions and predict plane parameters along with instance segmentation masks and per-pixel depth values.\"},{\"question\":\"How does PlaneRCNN improve segmentation during training?\",\"answer\":\"It refines all segmentation masks jointly using a novel loss that enforces consistency with a nearby view during training.\"}]","PlaneRCNN - 3D Plane Detection and Reconstruction from a Single Image | PDF",1791288239,25,[146,150,154,158],{"page_no":8,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/13755d227d1cf149b6818bbe9c481f43.webp",983,1272,{"page_no":14,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/2d4181dcd1d592e8451df2cf304b2fc5.webp",982,1270,{"page_no":81,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/804911e88d29d7e8794b8c24b6b539df.webp",981,1269,{"page_no":19,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/4c3e77569464d942103b224a7935e135.webp",980,1268]