[{"data":1,"prerenderedAt":1047},["ShallowReactive",2],{"method-orbslam2015":3},{"method":4,"reference":60,"equipment":80,"figures":129,"results":130},{"id":5,"label":6,"shortName":7,"title":8,"year":9,"era":10,"cluster":11,"scope":12,"keyIdeaZh":13,"keyIdeaEn":14,"fulltextStatus":15,"publicationStatus":16,"recommendation":17,"constructionRelevance":18,"validationEnvironment":19,"strengths":21,"limitations":25,"sensors":34,"platform":36,"estimator":40,"association":41,"timeModel":42,"deskew":43,"loopClosure":44,"globalOptimization":45,"mapRepresentation":46,"prior":47,"outputGeometry":48,"compute":49,"codeUrl":50,"codeLicense":51,"relatedVersions":52},"orbslam2015","Mur-Artal et al., 2015","ORB-SLAM","ORB-SLAM: A Versatile and Accurate Monocular SLAM System",2015,"classic","C08","full_slam_with_global_correction","ORB-SLAM 以同一組 ORB 特徵同時支援追蹤、局部建圖、重定位（relocalization）與迴圈閉合（loop closure），分成三個平行執行緒。系統以共視圖（covisibility graph）限定局部 BA 範圍，偵測到迴圈後估計相似變換 Sim(3) 以校正單眼尺度漂移，再於稀疏的 Essential Graph 上做位姿圖最佳化。寬鬆建立、嚴格剔除關鍵影格與地圖點的策略使地圖只在場景內容改變時成長。","ORB-SLAM uses one ORB feature type for tracking, mapping, relocalization and loop closing, with covisibility-limited local BA and Sim(3) Essential-Graph optimisation to correct monocular scale drift.","full_text_reviewed","peer_reviewed_published","background","論文未報告營建工地測試；資料集涵蓋室內（TUM RGB-D）、戶外車載（KITTI）與校園機器人（NewCollege）。單眼尺度需另行對齊，對工程量測不足以單獨提供公制幾何（推論）。",[20],"public_benchmark",[22,23,24],"Evaluated on 27 sequences from popular datasets (abstract)","Wide-baseline relocalization and loop closing with automatic initialisation (abstract)","Real-time on CPU without GPU (Sec. IX-A)",[26,27,28,29,30,31,32,33],"Monocular map is sparse; authors list denser reconstruction as future work (Sec. IX-C)","Accuracy reported after aligning scale with ground truth, i.e. monocular scale is not metric (Sec. IX-A)","Authors acknowledge direct methods are more robust to blur and low texture (Sec. IX-B)","Refuses to initialise on fr3_nstr_tex_far, a planar scene with twofold ambiguity (Sec. VIII-B, Table III)","Fails on KITTI 01, a highway with few trackable close objects (Sec. VIII-E, Table V)","Without loops (KITTI 08) scale drift is not corrected; error about 5% of the trajectory dimension (Sec. VIII-E, Fig. 12)","The large NewCollege loop traversed in opposite directions was not detected by place recognition and does not align (Sec. VIII-A, Fig. 6)","Points at infinity (without sufficient parallax) are not used in tracking (Sec. IX-C)",[35],"monocular camera",[37,38,39],"handheld","wheeled UGV","vehicle","motion-only BA in tracking, local BA in mapping, pose-graph optimisation over Sim(3) constraints on the Essential Graph; Levenberg-Marquardt in g2o (Sec. III-B)","ORB (oriented multi-scale FAST with 256-bit descriptor): FAST corners on 8 scale levels (factor 1.2), 1000 corners for 512x384 to 752x480 images and 2000 for KITTI 1241x376, spread by a per-level grid; constant-velocity prediction with guided search of last-frame points, then projection of a covisibility-based local map (keyframes sharing points plus their neighbours) with viewing-angle and scale-range checks; DBoW2 bag-of-words place recognition with an offline ORB vocabulary, covisibility-grouped scores and all matches above 75% of the best score","discrete poses (keyframes)","not_applicable","Per keyframe, BoW candidates scoring above the lowest score among covisible neighbours (theta_min 30) are kept and a loop is accepted only after three consecutive consistent candidates; a Sim(3) is estimated from 3D-3D ORB matches with Horn's method inside RANSAC and refined with guided matching, serving as geometric validation; duplicated points are fused and covisibility edges added; then Sim(3) pose-graph optimisation on the Essential Graph (spanning tree, covisibility edges with theta_min 100, loop edges; 10 LM iterations in the experiments)","Sim(3) pose-graph optimisation over the Essential Graph after each loop; the running system performs no full BA. In an offline test, 20 LM iterations of full BA at the end of each sequence slightly improved loopy KITTI trajectories (KITTI 00: 6.68 to 5.33 m RMSE) with negligible effect on open ones; on KITTI 09, full BA alone converged poorly (48.77 m before loop closing, 18.82 m after 100 iterations) whereas Essential Graph optimisation reached 8.36 to 8.95 m","sparse map points plus keyframes with covisibility graph","No prior map; assumes calibrated camera intrinsics (keypoints undistorted when a distortion model is given) and an ORB visual vocabulary trained offline from a large image set","keyframe trajectory and sparse 3D map points (up to scale in monocular mode)","Intel Core i7-4700MQ (4 cores at 2.40 GHz) with 8 GB RAM, no GPU; the three threads run alongside ROS, so medians over several runs are reported. On NewCollege (512x382, 20 fps) the tracking thread takes a median 30.57 ms per frame (about 25 to 30 Hz) and local mapping a median 383.59 ms per keyframe, dominated by local BA (median 296.08 ms); each of the six loop corrections takes 0.51 to 4.69 s in total","https:\u002F\u002Fgithub.com\u002Fraulmur\u002FORB_SLAM","GPLv3 (LICENSE.txt header)",[53,57],{"relation":54,"title":55,"doi_or_url":56},"preprint","ORB-SLAM: a Versatile and Accurate Monocular SLAM System (arXiv v1-v2)","https:\u002F\u002Farxiv.org\u002Fabs\u002F1502.00956",{"relation":58,"title":59,"doi_or_url":50},"code_release","ORB_SLAM",{"id":5,"kind":61,"shortName":7,"title":8,"authors":62,"year":9,"venue":66,"venueType":67,"publisher":68,"volumeIssuePages":69,"doi":70,"arxivId":71,"url":56,"firstPublicDate":72,"publicationStatus":16,"metadataStatus":73,"fulltextStatus":15,"era":10,"classicReason":74,"codeUrl":50,"cluster":11,"topics":75,"mdpi":76,"verification":77,"label":6,"fulltextRoute":78,"versionRead":79,"addedByCensus":76},"method",[63,64,65],"Raul Mur-Artal","J. M. M. Montiel","Juan D. Tardos","IEEE Transactions on Robotics","journal","IEEE","31(5):1147-1163","10.1109\u002Ftro.2015.2463671","1502.00956","2015-02-03","metadata_verified","principle reused and reproducible baseline: ORB features shared by tracking, mapping and place recognition, covisibility\u002Fessential graph and Sim(3) loop closure form the base of ORB-SLAM2 and ORB-SLAM3.",[11],false,"confirmed","arXiv","arXiv 1502.00956v2 (2015-09-18), accepted manuscript with the IEEE T-RO copyright notice on a cover page (18 PDF pages, journal pages numbered up to 17); IEEE Xplore version of record not compared",[81,88,95,99,105,111,117,121,125],{"category":82,"model":83,"canonical":83,"role":84,"dataset":85,"specs":86,"locator":87},"compute","Intel Core i7-4700MQ","compute for runtime",null,"4 cores at 2.40 GHz, 8 GB RAM; no GPU","Sec. VIII",{"category":89,"model":90,"canonical":90,"role":91,"dataset":92,"specs":93,"locator":94},"stereo_camera","NewCollege stereo camera (model not stated)","dataset sensor","NewCollege","20 fps, 512x382; processed as monocular input","Sec. VIII-A",{"category":96,"model":97,"canonical":97,"role":91,"dataset":92,"specs":98,"locator":94},"platform","robot traversing a campus and adjacent parks (NewCollege)","2.2 km sequence with several loops and fast rotations",{"category":100,"model":101,"canonical":101,"role":91,"dataset":102,"specs":103,"locator":104},"rgbd","TUM RGB-D benchmark camera (model not stated)","TUM RGB-D","hand-held indoor sequences; images used as monocular input","Sec. VIII, VIII-B",{"category":106,"model":107,"canonical":107,"role":108,"dataset":102,"specs":109,"locator":110},"other","external motion capture system (model not stated)","reference or ground truth","provides TUM RGB-D ground truth","Sec. VIII-B",{"category":112,"model":113,"canonical":113,"role":91,"dataset":114,"specs":115,"locator":116},"camera","KITTI camera (model not stated)","KITTI odometry","10 fps, 1241x376","Sec. V-A, VIII-E",{"category":96,"model":118,"canonical":118,"role":91,"dataset":114,"specs":119,"locator":120},"car (KITTI)","driven around a residential area; 11 sequences","Sec. VIII-E",{"category":122,"model":123,"canonical":123,"role":108,"dataset":114,"specs":124,"locator":120},"gnss","GPS (KITTI ground truth, model not stated)","ground truth from GPS and a Velodyne laser scanner",{"category":126,"model":127,"canonical":127,"role":108,"dataset":114,"specs":128,"locator":120},"lidar","Velodyne laser scanner (KITTI ground truth, model not stated)","used with GPS for the ground truth",[],{"totalRows":131,"groupCount":132,"groups":133,"others":967},150,19,[134,274,559,829],{"slug":135,"group":136,"sourceId":5,"sourceLabel":6,"table":137,"selfRows":138,"metrics":139,"seqs":151,"entrants":185,"cells":190,"outcomes":266,"locators":268,"hardware":269,"wordings":271,"notes":272},"orbslam2015-table-v","orbslam2015:Table V","Table V",33,[140,145,147],{"label":141,"unit":142,"statistic":143,"alignment":144},"RMSE (m), ORB-SLAM keyframe trajectory","m","RMSE","Sim3",{"label":146,"unit":142,"statistic":143,"alignment":144},"RMSE (m) after Global BA (20 its.)",{"label":148,"unit":149,"statistic":150,"alignment":43},"Time BA (s) for 20 iterations of full BA","s","not_reported",[152,155,158,161,164,167,170,173,176,179,182],{"dataset":114,"sequence":153,"environment":154},"00","outdoor, car driven around a residential area (Sec. VIII-E); map 564x496 m",{"dataset":114,"sequence":156,"environment":157},"01","outdoor, car driven around a residential area (Sec. VIII-E); map 1157x1827 m",{"dataset":114,"sequence":159,"environment":160},"02","outdoor, car driven around a residential area (Sec. VIII-E); map 599x946 m",{"dataset":114,"sequence":162,"environment":163},"03","outdoor, car driven around a residential area (Sec. VIII-E); map 471x199 m",{"dataset":114,"sequence":165,"environment":166},"04","outdoor, car driven around a residential area (Sec. VIII-E); map 0.5x394 m",{"dataset":114,"sequence":168,"environment":169},"05","outdoor, car driven around a residential area (Sec. VIII-E); map 479x426 m",{"dataset":114,"sequence":171,"environment":172},"06","outdoor, car driven around a residential area (Sec. VIII-E); map 23x457 m",{"dataset":114,"sequence":174,"environment":175},"07","outdoor, car driven around a residential area (Sec. VIII-E); map 191x209 m",{"dataset":114,"sequence":177,"environment":178},"08","outdoor, car driven around a residential area (Sec. VIII-E); map 808x391 m",{"dataset":114,"sequence":180,"environment":181},"09","outdoor, car driven around a residential area (Sec. VIII-E); map 465x568 m",{"dataset":114,"sequence":183,"environment":184},"10","outdoor, car driven around a residential area (Sec. VIII-E); map 671x177 m",[186,188],{"name":7,"methodId":5,"linkable":187,"proposed":187,"self":187},true,{"name":189,"methodId":5,"linkable":187,"proposed":187,"self":187},"ORB-SLAM + Global BA (20 its.)",[191,195,198,201,202,203,204,206,208,210,213,215,217,220,222,224,227,229,231,234,236,238,241,243,245,248,250,252,255,257,259,262,264],[192,192,192,193,194,192,194,194,192],0,6.68,-1,[196,196,192,197,194,192,194,194,192],1,5.33,[196,199,192,200,194,192,192,194,192],2,24.83,[192,192,196,85,192,192,194,194,192],[196,196,196,85,192,192,194,194,192],[196,199,196,85,192,192,192,194,192],[192,192,199,205,194,192,194,194,192],21.75,[196,196,199,207,194,192,194,194,192],21.28,[196,199,199,209,194,192,192,194,192],30.07,[192,192,211,212,194,192,194,194,192],3,1.59,[196,196,211,214,194,192,194,194,192],1.51,[196,199,211,216,194,192,192,194,192],4.88,[192,192,218,219,194,192,194,194,192],4,1.79,[196,196,218,221,194,192,194,194,192],1.62,[196,199,218,223,194,192,192,194,192],1.58,[192,192,225,226,194,192,194,194,192],5,8.23,[196,196,225,228,194,192,194,194,192],4.85,[196,199,225,230,194,192,192,194,192],15.2,[192,192,232,233,194,192,194,194,192],6,14.68,[196,196,232,235,194,192,194,194,192],12.34,[196,199,232,237,194,192,192,194,192],7.78,[192,192,239,240,194,192,194,194,192],7,3.36,[196,196,239,242,194,192,194,194,192],2.26,[196,199,239,244,194,192,192,194,192],6.28,[192,192,246,247,194,192,194,194,192],8,46.58,[196,196,246,249,194,192,194,194,192],46.68,[196,199,246,251,194,192,192,194,192],25.6,[192,192,253,254,194,192,194,194,192],9,7.62,[196,196,253,256,194,192,194,194,192],6.62,[196,199,253,258,194,192,192,194,192],11.33,[192,192,260,261,194,192,194,194,192],10,8.68,[196,196,260,263,194,192,194,194,192],8.8,[196,199,260,265,194,192,192,194,192],7.64,[267],"failed (sequence not processed: highway with few trackable close objects)",[137],[270],"Intel Core i7-4700MQ, 8 GB RAM",[],[273],"KITTI odometry, keyframe trajectory RMSE (m), median of 5 executions, Sim(3) alignment; right columns after 20 LM iterations of full BA at the end of the sequence; X = sequence 01 not processed",{"slug":275,"group":276,"sourceId":277,"sourceLabel":278,"table":279,"selfRows":280,"metrics":281,"seqs":284,"entrants":310,"cells":339,"outcomes":552,"locators":554,"hardware":555,"wordings":556,"notes":557},"svo2017-table-i","svo2017:Table I","svo2017","Forster et al., 2017b","Table I",22,[282],{"label":283,"unit":142,"statistic":143,"alignment":144},"absolute translation error (RMSE)",[285,289,291,293,295,297,300,302,304,306,308],{"dataset":286,"sequence":287,"environment":288},"EuRoC","Machine Hall 01","indoor machine hall, micro aerial vehicle",{"dataset":286,"sequence":290,"environment":288},"Machine Hall 02",{"dataset":286,"sequence":292,"environment":288},"Machine Hall 03",{"dataset":286,"sequence":294,"environment":288},"Machine Hall 04",{"dataset":286,"sequence":296,"environment":288},"Machine Hall 05",{"dataset":286,"sequence":298,"environment":299},"Vicon Room 1 01","indoor Vicon room, micro aerial vehicle",{"dataset":286,"sequence":301,"environment":299},"Vicon Room 1 02",{"dataset":286,"sequence":303,"environment":299},"Vicon Room 1 03",{"dataset":286,"sequence":305,"environment":299},"Vicon Room 2 01",{"dataset":286,"sequence":307,"environment":299},"Vicon Room 2 02",{"dataset":286,"sequence":309,"environment":299},"Vicon Room 2 03",[311,313,315,317,319,321,323,325,327,329,331,334,336],{"name":312,"methodId":277,"linkable":187,"proposed":187,"self":76},"SVO (stereo)",{"name":314,"methodId":277,"linkable":187,"proposed":187,"self":76},"SVO (stereo, edgelets)",{"name":316,"methodId":277,"linkable":187,"proposed":187,"self":76},"SVO (stereo, edgelets + prior)",{"name":318,"methodId":277,"linkable":187,"proposed":187,"self":76},"SVO (stereo, bundle adjustment)",{"name":320,"methodId":277,"linkable":187,"proposed":187,"self":76},"SVO (monocular)",{"name":322,"methodId":277,"linkable":187,"proposed":187,"self":76},"SVO (monocular, edgelets)",{"name":324,"methodId":277,"linkable":187,"proposed":187,"self":76},"SVO (monocular, edgelets + prior)",{"name":326,"methodId":277,"linkable":187,"proposed":187,"self":76},"SVO (monocular, bundle adjustment)",{"name":328,"methodId":5,"linkable":187,"proposed":76,"self":187},"ORB-SLAM (monocular, no loop-closure)",{"name":330,"methodId":5,"linkable":187,"proposed":76,"self":187},"ORB-SLAM (monocular, no loop, real-time)",{"name":332,"methodId":333,"linkable":187,"proposed":76,"self":76},"DSO (monocular)","dso2018",{"name":335,"methodId":333,"linkable":187,"proposed":76,"self":76},"DSO (monocular, real-time)",{"name":337,"methodId":338,"linkable":187,"proposed":76,"self":76},"LSD-SLAM (monocular, no loop-closure)","lsdslam2014",[340,342,343,345,346,348,349,351,353,355,357,359,361,364,365,367,368,369,371,372,374,375,377,379,380,381,383,385,386,387,388,390,392,394,395,396,398,399,401,403,405,407,408,409,411,412,413,415,417,419,421,423,425,426,428,429,430,432,434,436,437,439,441,443,445,447,448,449,450,451,453,454,455,456,458,460,461,463,465,467,468,469,470,471,473,475,476,477,479,480,481,483,485,486,487,488,489,490,491,492,494,496,498,500,501,502,503,504,505,506,507,508,509,510,512,513,514,515,517,519,520,521,522,523,524,525,526,528,530,532,533,534,535,537,538,539,540,542,543,545,547,549,551],[192,192,192,341,194,192,194,194,192],0.08,[196,192,192,341,194,192,194,194,192],[199,192,192,344,194,192,194,194,192],0.04,[211,192,192,344,194,192,194,194,192],[218,192,192,347,194,192,194,194,192],0.17,[225,192,192,347,194,192,194,194,192],[232,192,192,350,194,192,194,194,192],0.1,[239,192,192,352,194,192,194,194,192],0.06,[246,192,192,354,194,192,194,194,192],0.02,[253,192,192,356,194,192,194,194,192],0.61,[260,192,192,358,194,192,194,194,192],0.05,[360,192,192,358,194,192,194,194,192],11,[362,192,192,363,194,192,194,194,192],12,0.18,[192,192,196,341,194,192,194,194,192],[196,192,196,366,194,192,194,194,192],0.07,[199,192,196,366,194,192,194,194,192],[211,192,196,358,194,192,194,194,192],[218,192,196,370,194,192,194,194,192],0.27,[225,192,196,370,194,192,194,194,192],[232,192,196,373,194,192,194,194,192],0.12,[239,192,196,366,194,192,194,194,192],[246,192,196,376,194,192,194,194,192],0.03,[253,192,196,378,194,192,194,194,192],0.72,[260,192,196,358,194,192,194,194,192],[360,192,196,358,194,192,194,194,192],[362,192,196,382,194,192,194,194,192],0.56,[192,192,199,384,194,192,194,194,192],0.29,[196,192,199,370,194,192,194,194,192],[199,192,199,370,194,192,194,194,192],[211,192,199,352,194,192,194,194,192],[218,192,199,389,194,192,194,194,192],0.43,[225,192,199,391,194,192,194,194,192],0.42,[232,192,199,393,194,192,194,194,192],0.41,[239,192,199,85,192,192,194,194,192],[246,192,199,376,194,192,194,194,192],[253,192,199,397,194,192,194,194,192],1.7,[260,192,199,363,194,192,194,194,192],[360,192,199,400,194,192,194,194,192],0.26,[362,192,199,402,194,192,194,194,192],2.69,[192,192,211,404,194,192,194,194,192],2.67,[196,192,211,406,194,192,194,194,192],2.42,[199,192,211,347,194,192,194,194,192],[211,192,211,85,192,192,194,194,192],[218,192,211,410,194,192,194,194,192],1.36,[225,192,211,196,194,192,194,194,192],[232,192,211,389,194,192,194,194,192],[239,192,211,414,194,192,194,194,192],0.4,[246,192,211,416,194,192,194,194,192],0.22,[253,192,211,418,194,192,194,194,192],6.32,[260,192,211,420,194,192,194,194,192],2.5,[360,192,211,422,194,192,194,194,192],0.24,[362,192,211,424,194,192,194,194,192],2.13,[192,192,218,389,194,192,194,194,192],[196,192,218,427,194,192,194,194,192],0.54,[199,192,218,373,194,192,194,194,192],[211,192,218,373,194,192,194,194,192],[218,192,218,431,194,192,194,194,192],0.51,[225,192,218,433,194,192,194,194,192],0.6,[232,192,218,435,194,192,194,194,192],0.3,[239,192,218,85,192,192,194,194,192],[246,192,218,438,194,192,194,194,192],0.71,[253,192,218,440,194,192,194,194,192],5.66,[260,192,218,442,194,192,194,194,192],0.11,[360,192,218,444,194,192,194,194,192],0.15,[362,192,218,446,194,192,194,194,192],0.85,[192,192,225,358,194,192,194,194,192],[196,192,225,344,194,192,194,194,192],[199,192,225,344,194,192,194,194,192],[211,192,225,358,194,192,194,194,192],[218,192,225,452,194,192,194,194,192],0.2,[225,192,225,416,194,192,194,194,192],[232,192,225,366,194,192,194,194,192],[239,192,225,358,194,192,194,194,192],[246,192,225,457,194,192,194,194,192],0.16,[253,192,225,459,194,192,194,194,192],1.35,[260,192,225,373,194,192,194,194,192],[360,192,225,462,194,192,194,194,192],0.47,[362,192,225,464,194,192,194,194,192],1.24,[192,192,232,466,194,192,194,194,192],0.09,[196,192,232,341,194,192,194,194,192],[199,192,232,344,194,192,194,194,192],[211,192,232,358,194,192,194,194,192],[218,192,232,462,194,192,194,194,192],[225,192,232,472,194,192,194,194,192],0.35,[232,192,232,474,194,192,194,194,192],0.21,[239,192,232,85,192,192,194,194,192],[246,192,232,363,194,192,194,194,192],[253,192,232,478,194,192,194,194,192],0.58,[260,192,232,442,194,192,194,194,192],[360,192,232,350,194,192,194,194,192],[362,192,232,482,194,192,194,194,192],1.11,[192,192,239,484,194,192,194,194,192],0.36,[196,192,239,484,194,192,194,194,192],[199,192,239,366,194,192,194,194,192],[211,192,239,85,192,192,194,194,192],[218,192,239,85,192,192,194,194,192],[225,192,239,85,192,192,194,194,192],[232,192,239,85,192,192,194,194,192],[239,192,239,85,192,192,194,194,192],[246,192,239,493,194,192,194,194,192],0.78,[253,192,239,495,194,192,194,194,192],0.63,[260,192,239,497,194,192,194,194,192],0.93,[360,192,239,499,194,192,194,194,192],0.66,[362,192,239,85,192,192,194,194,192],[192,192,246,466,194,192,194,194,192],[196,192,246,366,194,192,194,194,192],[199,192,246,358,194,192,194,194,192],[211,192,246,358,194,192,194,194,192],[218,192,246,435,194,192,194,194,192],[225,192,246,400,194,192,194,194,192],[232,192,246,442,194,192,194,194,192],[239,192,246,85,192,192,194,194,192],[246,192,246,354,194,192,194,194,192],[253,192,246,511,194,192,194,194,192],0.53,[260,192,246,344,194,192,194,194,192],[360,192,246,358,194,192,194,194,192],[362,192,246,85,192,192,194,194,192],[192,192,253,516,194,192,194,194,192],0.52,[196,192,253,518,194,192,194,194,192],0.14,[199,192,253,466,194,192,194,194,192],[211,192,253,85,192,192,194,194,192],[218,192,253,462,194,192,194,194,192],[225,192,253,414,194,192,194,194,192],[232,192,253,442,194,192,194,194,192],[239,192,253,85,192,192,194,194,192],[246,192,253,474,194,192,194,194,192],[253,192,253,527,194,192,194,194,192],0.68,[260,192,253,529,194,192,194,194,192],0.13,[360,192,253,531,194,192,194,194,192],0.19,[362,192,253,85,192,192,194,194,192],[192,192,260,85,192,192,194,194,192],[196,192,260,85,192,192,194,194,192],[199,192,260,536,194,192,194,194,192],0.79,[211,192,260,85,192,192,194,194,192],[218,192,260,85,192,192,194,194,192],[225,192,260,85,192,192,194,194,192],[232,192,260,541,194,192,194,194,192],1.08,[239,192,260,85,192,192,194,194,192],[246,192,260,544,194,192,194,194,192],1.25,[253,192,260,546,194,192,194,194,192],1.06,[260,192,260,548,194,192,194,194,192],1.16,[360,192,260,550,194,192,194,194,192],1.19,[362,192,260,85,192,192,194,194,192],[553],"failed",[279],[],[],[558],"EuRoC; absolute translation error RMSE of keyframe positions after least-squares translation and scale alignment, averaged over five runs; loop closure deactivated for ORB-SLAM and LSD-SLAM; ORB-SLAM and DSO values taken from the DSO paper [42] with and without enforced real-time execution; x = tracking failed (version of record Table I)",{"slug":560,"group":561,"sourceId":562,"sourceLabel":563,"table":564,"selfRows":565,"metrics":566,"seqs":572,"entrants":598,"cells":611,"outcomes":822,"locators":823,"hardware":824,"wordings":825,"notes":826},"cnnslam2017-table-1","cnnslam2017:Table 1","cnnslam2017","Tateno et al., 2017","Table 1",20,[567,569],{"label":568,"unit":142,"statistic":143,"alignment":150},"Abs. Trajectory Error [m]",{"label":570,"unit":571,"statistic":43,"alignment":43},"Perc. Correct Depth (error \u003C 10%)","%",[573,577,579,581,583,585,587,590,592,594],{"dataset":574,"sequence":575,"environment":576},"ICL-NUIM","office0","synthetic indoor (ICL-NUIM)",{"dataset":574,"sequence":578,"environment":576},"office1",{"dataset":574,"sequence":580,"environment":576},"office2",{"dataset":574,"sequence":582,"environment":576},"living0",{"dataset":574,"sequence":584,"environment":576},"living1",{"dataset":574,"sequence":586,"environment":576},"living2",{"dataset":102,"sequence":588,"environment":589},"fr3\u002Flong_office_household","real indoor office (Kinect)",{"dataset":102,"sequence":591,"environment":589},"fr3\u002Fnostructure_texture_near_withloop",{"dataset":102,"sequence":593,"environment":589},"fr3\u002Fstructure_texture_far",{"dataset":595,"sequence":596,"environment":597},"ICL-NUIM and TUM RGB-D","average of 9 sequences","indoor",[599,601,603,605,607,609],{"name":600,"methodId":85,"linkable":76,"proposed":187,"self":76},"CNN-SLAM (Our Method)",{"name":602,"methodId":338,"linkable":187,"proposed":76,"self":76},"LSD-BS [4] (LSD-SLAM bootstrapped with ground-truth depth)",{"name":604,"methodId":338,"linkable":187,"proposed":76,"self":76},"LSD [4] (LSD-SLAM)",{"name":606,"methodId":5,"linkable":187,"proposed":76,"self":187},"ORB [20] (ORB-SLAM)",{"name":608,"methodId":85,"linkable":76,"proposed":76,"self":76},"Laina [16] (CNN depth fed to point-based fusion)",{"name":610,"methodId":85,"linkable":76,"proposed":76,"self":76},"Remode [23] (REMODE, poses from LSD-BS)",[612,614,616,618,619,621,623,625,627,629,631,633,635,636,638,639,641,643,645,647,649,651,653,655,657,659,661,663,665,667,669,670,672,674,676,678,680,682,684,686,688,689,691,693,694,696,697,699,701,702,704,706,708,710,712,714,716,718,720,722,724,726,728,730,732,734,736,738,740,742,744,746,748,750,752,754,756,758,760,762,764,766,768,770,772,774,775,777,779,781,783,785,787,789,791,793,795,796,798,800,802,804,806,808,810,812,814,816,818,820],[192,192,192,613,194,192,194,194,192],0.266,[196,192,192,615,194,192,194,194,192],0.587,[199,192,192,617,194,192,194,194,192],0.528,[211,192,192,389,194,192,194,194,192],[218,192,192,620,194,192,194,194,192],0.337,[192,196,192,622,194,192,194,194,196],19.41,[196,196,192,624,194,192,194,194,196],0.603,[199,196,192,626,194,192,194,194,196],0.335,[211,196,192,628,194,192,194,194,196],0.018,[218,196,192,630,194,192,194,194,196],17.194,[225,196,192,632,194,192,194,194,196],4.479,[192,192,196,634,194,192,194,194,192],0.157,[196,192,196,536,194,192,194,194,192],[199,192,196,637,194,192,194,194,192],0.768,[211,192,196,493,194,192,194,194,192],[218,192,196,640,194,192,194,194,192],0.218,[192,196,196,642,194,192,194,194,196],29.15,[196,196,196,644,194,192,194,194,196],4.759,[199,196,196,646,194,192,194,194,196],0.038,[211,196,196,648,194,192,194,194,196],0.023,[218,196,196,650,194,192,194,194,196],20.838,[225,196,196,652,194,192,194,194,196],3.132,[192,192,199,654,194,192,194,194,192],0.213,[196,192,199,656,194,192,194,194,192],0.172,[199,192,199,658,194,192,194,194,192],0.794,[211,192,199,660,194,192,194,194,192],0.86,[218,192,199,662,194,192,194,194,192],0.509,[192,196,199,664,194,192,194,194,196],37.226,[196,196,199,666,194,192,194,194,196],1.435,[199,196,199,668,194,192,194,194,196],0.078,[211,196,199,344,194,192,194,194,196],[218,196,199,671,194,192,194,194,196],30.639,[225,196,199,673,194,192,194,194,196],16.7081,[192,192,211,675,194,192,194,194,192],0.196,[196,192,211,677,194,192,194,194,192],0.894,[199,192,211,679,194,192,194,194,192],0.516,[211,192,211,681,194,192,194,194,192],0.493,[218,192,211,683,194,192,194,194,192],0.23,[192,196,211,685,194,192,194,194,196],12.84,[196,196,211,687,194,192,194,194,196],1.443,[199,196,211,484,194,192,194,194,196],[211,196,211,690,194,192,194,194,196],0.027,[218,196,211,692,194,192,194,194,196],15.008,[225,196,211,632,194,192,194,194,196],[192,192,218,695,194,192,194,194,192],0.059,[196,192,218,427,194,192,194,194,192],[199,192,218,698,194,192,194,194,192],0.48,[211,192,218,700,194,192,194,194,192],0.129,[218,192,218,352,194,192,194,194,192],[192,196,218,703,194,192,194,194,196],13.038,[196,196,218,705,194,192,194,194,196],3.03,[199,196,218,707,194,192,194,194,196],0.057,[211,196,218,709,194,192,194,194,196],0.021,[218,196,218,711,194,192,194,194,196],11.449,[225,196,218,713,194,192,194,194,196],2.427,[192,192,225,715,194,192,194,194,192],0.323,[196,192,225,717,194,192,194,194,192],0.211,[199,192,225,719,194,192,194,194,192],0.667,[211,192,225,721,194,192,194,194,192],0.663,[218,192,225,723,194,192,194,194,192],0.38,[192,196,225,725,194,192,194,194,196],26.56,[196,196,225,727,194,192,194,194,196],1.807,[199,196,225,729,194,192,194,194,196],0.167,[211,196,225,731,194,192,194,194,196],0.014,[218,196,225,733,194,192,194,194,196],33.01,[225,196,225,735,194,192,194,194,196],8.681,[192,192,232,737,194,192,194,194,192],0.542,[196,192,232,739,194,192,194,194,192],1.717,[199,192,232,741,194,192,194,194,192],1.826,[211,192,232,743,194,192,194,194,192],1.206,[218,192,232,745,194,192,194,194,192],0.809,[192,196,232,747,194,192,194,194,196],12.477,[196,196,232,749,194,192,194,194,196],3.797,[199,196,232,751,194,192,194,194,196],0.086,[211,196,232,753,194,192,194,194,196],0.031,[218,196,232,755,194,192,194,194,196],12.982,[225,196,232,757,194,192,194,194,196],9.548,[192,192,239,759,194,192,194,194,192],0.243,[196,192,239,761,194,192,194,194,192],0.106,[199,192,239,763,194,192,194,194,192],0.436,[211,192,239,765,194,192,194,194,192],0.495,[218,192,239,767,194,192,194,194,192],1.337,[192,196,239,769,194,192,194,194,196],24.077,[196,196,239,771,194,192,194,194,196],3.966,[199,196,239,773,194,192,194,194,196],0.882,[211,196,239,695,194,192,194,194,196],[218,196,239,776,194,192,194,194,196],15.412,[225,196,239,778,194,192,194,194,196],12.651,[192,192,246,780,194,192,194,194,192],0.214,[196,192,246,782,194,192,194,194,192],0.037,[199,192,246,784,194,192,194,194,192],0.937,[211,192,246,786,194,192,194,194,192],0.733,[218,192,246,788,194,192,194,194,192],0.724,[192,196,246,790,194,192,194,194,196],27.396,[196,196,246,792,194,192,194,194,196],6.449,[199,196,246,794,194,192,194,194,196],0.035,[211,196,246,690,194,192,194,194,196],[218,196,246,797,194,192,194,194,196],9.45,[225,196,246,799,194,192,194,194,196],6.739,[192,192,253,801,194,192,194,194,192],0.246,[196,192,253,803,194,192,194,194,192],0.562,[199,192,253,805,194,192,194,194,192],0.772,[211,192,253,807,194,192,194,194,192],0.643,[218,192,253,809,194,192,194,194,192],0.512,[192,196,253,811,194,192,194,194,196],22.464,[196,196,253,813,194,192,194,194,196],3.032,[199,196,253,815,194,192,194,194,196],0.226,[211,196,253,817,194,192,194,194,196],0.029,[218,196,253,819,194,192,194,194,196],18.452,[225,196,253,821,194,192,194,194,196],7.649,[],[564],[],[],[827,828],"Absolute trajectory error (RMSE of camera translation, TUM methodology) on ICL-NUIM and TUM sequences; CNN trained on NYU Depth v2 only; monocular baselines keep their scale ambiguity except LSD-BS","Percentage of key-frame depth values within 10% of ground-truth depth (accuracy and density together)",{"slug":830,"group":831,"sourceId":5,"sourceLabel":6,"table":832,"selfRows":833,"metrics":834,"seqs":838,"entrants":872,"cells":879,"outcomes":958,"locators":962,"hardware":963,"wordings":964,"notes":965},"orbslam2015-table-iii","orbslam2015:Table III","Table III",16,[835],{"label":836,"unit":837,"statistic":143,"alignment":144},"Absolute KeyFrame Trajectory RMSE","cm",[839,842,844,846,848,850,852,854,856,858,860,862,864,866,868,870],{"dataset":102,"sequence":840,"environment":841},"fr1_xyz","indoor, hand-held",{"dataset":102,"sequence":843,"environment":841},"fr2_xyz",{"dataset":102,"sequence":845,"environment":841},"fr1_floor",{"dataset":102,"sequence":847,"environment":841},"fr1_desk",{"dataset":102,"sequence":849,"environment":841},"fr2_360_kidnap",{"dataset":102,"sequence":851,"environment":841},"fr2_desk",{"dataset":102,"sequence":853,"environment":841},"fr3_long_office",{"dataset":102,"sequence":855,"environment":841},"fr3_nstr_tex_far",{"dataset":102,"sequence":857,"environment":841},"fr3_nstr_tex_near",{"dataset":102,"sequence":859,"environment":841},"fr3_str_tex_far",{"dataset":102,"sequence":861,"environment":841},"fr3_str_tex_near",{"dataset":102,"sequence":863,"environment":841},"fr2_desk_person",{"dataset":102,"sequence":865,"environment":841},"fr3_sit_xyz",{"dataset":102,"sequence":867,"environment":841},"fr3_sit_halfsph",{"dataset":102,"sequence":869,"environment":841},"fr3_walk_xyz",{"dataset":102,"sequence":871,"environment":841},"fr3_walk_halfsph",[873,874,877],{"name":7,"methodId":5,"linkable":187,"proposed":187,"self":187},{"name":875,"methodId":876,"linkable":187,"proposed":76,"self":76},"PTAM","ptam2007",{"name":878,"methodId":338,"linkable":187,"proposed":76,"self":76},"LSD-SLAM",[880,882,884,885,886,887,889,891,892,894,896,897,899,901,903,904,906,907,909,911,912,914,915,916,918,920,922,924,926,927,929,930,932,933,934,935,937,938,940,942,945,946,948,950,951,953,956,957],[192,192,192,881,194,192,194,194,192],0.9,[196,192,192,883,194,192,194,194,192],1.15,[199,192,192,253,194,192,194,194,192],[192,192,196,435,194,192,194,194,192],[196,192,196,452,194,192,194,194,192],[199,192,196,888,194,192,194,194,192],2.15,[192,192,199,890,194,192,194,194,192],2.99,[196,192,199,85,192,192,194,194,192],[199,192,199,893,194,192,194,194,192],38.07,[192,192,211,895,194,192,194,194,192],1.69,[196,192,211,85,192,192,194,194,192],[199,192,211,898,194,192,194,194,192],10.65,[192,192,218,900,194,192,194,194,192],3.81,[196,192,218,902,194,192,194,194,192],2.63,[199,192,218,85,192,192,194,194,192],[192,192,225,905,194,192,194,194,192],0.88,[196,192,225,85,192,192,194,194,192],[199,192,225,908,194,192,194,194,192],4.57,[192,192,232,910,194,192,194,194,192],3.45,[196,192,232,85,192,192,194,194,192],[199,192,232,913,194,192,194,194,192],38.53,[192,192,239,85,196,192,194,194,192],[196,192,239,85,199,192,194,194,192],[199,192,239,917,194,192,194,194,192],18.31,[192,192,246,919,194,192,194,194,192],1.39,[196,192,246,921,194,192,194,194,192],2.74,[199,192,246,923,194,192,194,194,192],7.54,[192,192,253,925,194,192,194,194,192],0.77,[196,192,253,497,194,192,194,194,192],[199,192,253,928,194,192,194,194,192],7.95,[192,192,260,223,194,192,194,194,192],[196,192,260,931,194,192,194,194,192],1.04,[199,192,260,85,192,192,194,194,192],[192,192,360,495,194,192,194,194,192],[196,192,360,85,192,192,194,194,192],[199,192,360,936,194,192,194,194,192],31.73,[192,192,362,536,194,192,194,194,192],[196,192,362,939,194,192,194,194,192],0.83,[199,192,362,941,194,192,194,194,192],7.73,[192,192,943,944,194,192,194,194,192],13,1.34,[196,192,943,85,192,192,194,194,192],[199,192,943,947,194,192,194,194,192],5.87,[192,192,949,464,194,192,194,194,192],14,[196,192,949,85,192,192,194,194,192],[199,192,949,952,194,192,194,194,192],12.44,[192,192,954,955,194,192,194,194,192],15,1.74,[196,192,954,85,192,192,194,194,192],[199,192,954,85,192,192,194,194,192],[959,960,961],"failed (tracking lost, significant portion not processed)","not_run (initialisation refused: twofold planar ambiguity detected)","two values reported, 4.92 \u002F 34.74 cm, from runs with the true and the corrupted planar initialisation (Sec. VIII-B)",[832],[],[],[966],"TUM RGB-D keyframe ATE RMSE (cm), median over 5 executions; ORB-SLAM, PTAM (two manually chosen initial frames) and LSD-SLAM (first 10 keyframes discarded) aligned with Sim(3); RGBD-SLAM trajectories from the benchmark website aligned with SE(3), Sim(3) value in brackets; X = tracking lost",[968,973,979,985,990,996,1000,1005,1012,1016,1022,1027,1032,1036,1042],{"group":969,"slug":970,"sourceLabel":6,"table":971,"selfRows":954,"datasets":972},"orbslam2015:Table VI","orbslam2015-table-vi","Table VI",[114],{"group":974,"slug":975,"sourceLabel":976,"table":977,"selfRows":239,"datasets":978},"d3vo2020:Table 4","d3vo2020-table-4","Yang et al., 2020a","Table 4",[114],{"group":980,"slug":981,"sourceLabel":976,"table":982,"selfRows":232,"datasets":983},"d3vo2020:Table 6","d3vo2020-table-6","Table 6",[984],"EuRoC MAV",{"group":986,"slug":987,"sourceLabel":6,"table":988,"selfRows":232,"datasets":989},"orbslam2015:Table II","orbslam2015-table-ii","Table II",[92],{"group":991,"slug":992,"sourceLabel":993,"table":994,"selfRows":225,"datasets":995},"deng2026_mcgs_slam:Table 11","deng2026-mcgs-slam-table-11","Deng & Gan, 2026","Table 11",[984],{"group":997,"slug":998,"sourceLabel":6,"table":279,"selfRows":218,"datasets":999},"orbslam2015:Table I","orbslam2015-table-i",[92],{"group":1001,"slug":1002,"sourceLabel":6,"table":1003,"selfRows":218,"datasets":1004},"orbslam2015:Table IV","orbslam2015-table-iv","Table IV",[102],{"group":1006,"slug":1007,"sourceLabel":1008,"table":1009,"selfRows":211,"datasets":1010},"asadi2018visionrobot:Table 2","asadi2018visionrobot-table-2","Asadi et al., 2018","Table 2",[1011],"authors' outdoor videos",{"group":1013,"slug":1014,"sourceLabel":278,"table":988,"selfRows":211,"datasets":1015},"svo2017:Table II","svo2017-table-ii",[286],{"group":1017,"slug":1018,"sourceLabel":1019,"table":1020,"selfRows":196,"datasets":1021},"dpvslam2024:Table 3","dpvslam2024-table-3","Lipson et al., 2024","Table 3",[286],{"group":1023,"slug":1024,"sourceLabel":1019,"table":977,"selfRows":196,"datasets":1025},"dpvslam2024:Table 4","dpvslam2024-table-4",[1026],"TartanAir",{"group":1028,"slug":1029,"sourceLabel":1030,"table":564,"selfRows":196,"datasets":1031},"droidslam2021:Table 1","droidslam2021-table-1","Teed & Deng, 2021",[1026],{"group":1033,"slug":1034,"sourceLabel":1030,"table":1020,"selfRows":196,"datasets":1035},"droidslam2021:Table 3","droidslam2021-table-3",[984],{"group":1037,"slug":1038,"sourceLabel":1039,"table":1009,"selfRows":196,"datasets":1040},"ghadimzadeh2025slamnde:Table 2","ghadimzadeh2025slamnde-table-2","Ghadimzadeh Alamdari et al., 2025",[1041],"Luleå SubT tunnel dataset (Koval et al. 2022)",{"group":1043,"slug":1044,"sourceLabel":1045,"table":988,"selfRows":196,"datasets":1046},"orbslam3_2021:Table II","orbslam3-2021-table-ii","Campos et al., 2021",[286],1790510656215]