{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:45:09Z","timestamp":1778258709248,"version":"3.51.4"},"reference-count":95,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,7]]},"DOI":"10.1109\/cvpr.2017.261","type":"proceedings-article","created":{"date-parts":[[2017,11,9]],"date-time":"2017-11-09T16:50:33Z","timestamp":1510246233000},"page":"2432-2443","source":"Crossref","is-referenced-by-count":3512,"title":["ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes"],"prefix":"10.1109","author":[{"given":"Angela","family":"Dai","sequence":"first","affiliation":[]},{"given":"Angel X.","family":"Chang","sequence":"additional","affiliation":[]},{"given":"Manolis","family":"Savva","sequence":"additional","affiliation":[]},{"given":"Maciej","family":"Halber","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Funkhouser","sequence":"additional","affiliation":[]},{"given":"Matthias","family":"Niessner","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.219"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.377"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925867"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/2661229.2661230"},{"key":"ref76","first-page":"634","article-title":"Sliding shapes for 3D object detection in depth images","author":"song","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref77","author":"song","year":"2015","journal-title":"Deep sliding shapes for amodal 3d object detection in rgb-d images"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130298"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630857"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_30"},{"key":"ref78","author":"song","year":"2016","journal-title":"Semantic scene completion from a single depth image"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095074"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_22"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.18"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907236"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248005"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2015.2459891"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-4640-7_8"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126500"},{"key":"ref60","author":"nguyen","year":"2016","journal-title":"A robust 3D-2D interactive tool for scene segmentation and annotation"},{"key":"ref62","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1145\/2508363.2508374","article-title":"Real-time 3D reconstruction at scale using voxel hashing","volume":"32","author":"nie\u00dfner","year":"2013","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-4640-7_10"},{"key":"ref63","article-title":"Occipital","year":"2016","journal-title":"Occipital Structure Sensor"},{"key":"ref28","author":"handa","year":"2015","journal-title":"Scene Understanding Real World Indoor Scenes With Synthetic Data"},{"key":"ref64","article-title":"Efficient inference in fully connected crfs with gaussian edge potentials","author":"phillip","year":"2011","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_23"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6094861"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.609"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907054"},{"key":"ref67","first-page":"2759","article-title":"RGB-(D) scene labeling: Features and algorithms","author":"ren","year":"2012","journal-title":"Computer Vision and Pattern Recog nition (CVPR) 2012 IEEE Conference on"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385661"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0090-8"},{"key":"ref2","author":"armeni","year":"2017","journal-title":"Joint 2d-3d-semantic data for indoor scene understanding"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33712-3_37"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.88"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.421"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2207676.2208303"},{"key":"ref24","article-title":"CloudCompare3D point cloud and mesh processing software","author":"girardeau-montaut","year":"2011","journal-title":"opensource project"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_44"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.79"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.266"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095075"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386219"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/2766887"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.161"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.349"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.458"},{"key":"ref91","first-page":"1912","article-title":"3D ShapeNets: A deep representation for volumetric shapes","author":"wu","year":"2015","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916669237"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2011.6092378"},{"key":"ref58","article-title":"Indoor segmentation and support inference from RGBD images","author":"nathan silberman","year":"2012","journal-title":"ECCV"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2014.2331215"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0296-z"},{"key":"ref55","article-title":"When can we use KinectFusion for ground truth acquisition","volume":"2","author":"meister","year":"2012","journal-title":"IROS Workshop Color-depth Camera Fusion in Robotics"},{"key":"ref54","author":"mccormac","year":"2016","journal-title":"Semanticfusion Dense 3d semantic mapping with convolutional neural networks"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353481"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12286"},{"key":"ref10","author":"choi","year":"2016","journal-title":"A large dataset of object scans"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/237170.237269"},{"key":"ref40","first-page":"640","article-title":"Fall detection using ceiling-mounted 3D depth camera","volume":"2","author":"kepski","year":"2014","journal-title":"Computer Vision Theory and Applications (VISAPP) 2014 International Conference on"},{"key":"ref12","author":"dai","year":"2016","journal-title":"BundleFusion Real-time globally consistent 3D reconstruction using on-the-fly surface re-integration"},{"key":"ref13","author":"dai","year":"2016","journal-title":"Shape completion using 3d-encoder-predictor cnns and shape synthesis"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2015.08.004"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225199"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/BTAS.2013.6712688"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385773"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2013.IX.027"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/7287.001.0001","author":"fellbaum","year":"1998","journal-title":"WordNet"},{"key":"ref83","article-title":"Human activity detection from RGBD images","volume":"64","author":"sung","year":"2011","journal-title":"Plan Activity and Intent Recognition"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000022288.19776.77"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493482"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2015.XI.001"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33863-2_43"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"key":"ref6","author":"chang","year":"2015","journal-title":"ShapeNet An Information-Rich 3D Model Repository"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.346"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.41"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.68"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/2751556"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2461940"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.356"},{"key":"ref88","author":"whelan","year":"2012","journal-title":"Kintinuous Spatially Extended KinectFusion"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299195"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.179"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12573"},{"key":"ref48","first-page":"3","article-title":"Learning discriminative representations from RGB-D video data","volume":"1","author":"liu","year":"2013","journal-title":"IJCAI"},{"key":"ref47","first-page":"740","article-title":"Microsoft Coco: Common objects in context","author":"lin","year":"2014","journal-title":"European Conference on Com- Puter Vision"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2015.XI.040"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.180"},{"key":"ref44","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913478446"}],"event":{"name":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Honolulu, HI","start":{"date-parts":[[2017,7,21]]},"end":{"date-parts":[[2017,7,26]]}},"container-title":["2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8097368\/8099483\/08099744.pdf?arnumber=8099744","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,3,27]],"date-time":"2020-03-27T08:33:58Z","timestamp":1585298038000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8099744\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7]]},"references-count":95,"URL":"https:\/\/doi.org\/10.1109\/cvpr.2017.261","relation":{},"subject":[],"published":{"date-parts":[[2017,7]]}}}