[{"data":1,"prerenderedAt":1016},["ShallowReactive",2],{"method-orbslam2_2017":3},{"method":4,"reference":61,"equipment":79,"figures":119,"results":120},{"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":33,"platform":37,"estimator":41,"association":42,"timeModel":43,"deskew":44,"loopClosure":45,"globalOptimization":46,"mapRepresentation":47,"prior":48,"outputGeometry":49,"compute":50,"codeUrl":51,"codeLicense":52,"relatedVersions":53},"orbslam2_2017","Mur-Artal & Tardos, 2017","ORB-SLAM2","ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras",2017,"recent","C08","full_slam_with_global_correction","ORB-SLAM2 將 ORB-SLAM 擴充到雙目（stereo）與 RGB-D 相機，把近距與遠距雙目特徵納入 BA，使尺度可觀測，迴圈閉合改以剛體 SE(3) 位姿圖最佳化並在另一執行緒進行全域 BA。系統另提供只做定位的地圖重用模式。作者明言目標是長期且全域一致的定位，而非最精細的稠密重建；論文中的稠密點雲是以估計的關鍵影格位姿反投影感測器深度圖所得。","ORB-SLAM2 extends ORB-SLAM to stereo and RGB-D with metric-scale BA, SE(3) loop closure plus full BA, and a map-reuse localization mode; its dense clouds are depth maps back-projected from estimated keyframe poses, not a jointly optimised dense map.","full_text_reviewed","peer_reviewed_published","background","論文未於營建工地測試；EuRoC 包含工業廠房（machine hall）無人機序列，但不等同營建工地。稠密點雲僅為深度圖依位姿反投影的視覺化，其幾何誤差未經評估（推論）。",[20],"public_benchmark",[22,23,24],"Evaluation on 29 public sequences (abstract)","Real-time on CPU (abstract)","Zero-drift localization in already mapped areas (Sec. V)",[26,27,28,29,30,31,32],"Goal is globally consistent localization rather than the most detailed dense reconstruction (Sec. II-B)","Stereo run failed on EuRoC V2_03_difficult (marked X in Table II)","freiburg2 TUM depth maps had a 4% scale bias that authors compensated, which may partly explain their better results (Sec. IV-C)","Stereo tracking is lost in parts of EuRoC V2_03_difficult because of severe motion blur; the authors note the sequence can be processed with IMU information (Sec. IV-B)","The KITTI 09 loop, visible only in a few frames at the end, is not detected (Sec. IV-A)","KITTI 01 highway: translation error is worse because few close points can be tracked at high speed and 10 Hz (Sec. IV-A, Table I)","Localization mode assumes no significant environment changes; its visual-odometry matches can accumulate drift in unmapped regions (Sec. III-F)",[34,35,36],"monocular camera","stereo","RGB-D",[38,39,40],"handheld","UAV","vehicle","BA with monocular and stereo constraints (motion-only, local, and full BA in a separate thread after pose-graph optimisation) (Sec. III, III-D)","ORB extracted on both rectified stereo images (or on the RGB image); a stereo keypoint (uL, vL, uR) comes from matching each left ORB along the same row with subpixel patch-correlation refinement; for RGB-D the depth d is converted to a virtual right coordinate uR = uL - fx*b\u002Fd with b approximated to 8 cm for Kinect and Asus Xtion; keypoints with depth below 40 times the baseline are close (triangulated from one frame, carry scale), others far (triangulated only from multiple views), unmatched ones stay monocular; DBoW2 place recognition as in ORB-SLAM","discrete poses (keyframes)","not_applicable","DBoW2 detection with geometric validation; rigid-body SE(3) pose-graph when stereo\u002Fdepth makes scale observable, followed by full BA (Sec. III-D)","pose-graph optimisation then full BA in a separate thread, with corrections propagated through the spanning tree (Sec. III-D)","sparse map points plus keyframes (covisibility graph, spanning tree)","No prior map in SLAM mode; the Localization Mode reuses a previously built map with local mapping and loop closing disabled. Assumes rectified stereo with known focal length, principal point and baseline; the RGB-D structured-light baseline is approximated to 8 cm; the 4% depth scale bias of TUM freiburg2 sequences was compensated in the authors' runs","keyframe trajectory and sparse map points; the dense point clouds shown are obtained by back-projecting sensor depth maps from estimated keyframe poses (Sec. IV-C, Fig. 7)","Intel Core i7-4790 desktop with 16 GB RAM, CPU only; each sequence run 5 times (median accuracy reported). Mean tracking time per frame 41.66 ms on EuRoC V2_02 (stereo 752x480, 20 Hz), 49.47 ms on KITTI 07 (stereo 1226x370, 10 Hz) and 25.58 ms on TUM fr3_office (RGB-D 640x480, 30 Hz), each below the frame period; local mapping 129.52 to 267.33 ms per keyframe; full BA after the single loop 349.25 to 1640.96 ms in a separate thread","https:\u002F\u002Fgithub.com\u002Fraulmur\u002FORB_SLAM2","GPLv3 (LICENSE.txt header)",[54,58],{"relation":55,"title":56,"doi_or_url":57},"preprint","ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras (arXiv)","https:\u002F\u002Farxiv.org\u002Fabs\u002F1610.06475",{"relation":59,"title":60,"doi_or_url":51},"code_release","ORB_SLAM2",{"id":5,"kind":62,"shortName":7,"title":8,"authors":63,"year":9,"venue":66,"venueType":67,"publisher":68,"volumeIssuePages":69,"doi":70,"arxivId":71,"url":57,"firstPublicDate":72,"publicationStatus":16,"metadataStatus":73,"fulltextStatus":15,"era":10,"classicReason":44,"codeUrl":51,"cluster":11,"topics":74,"mdpi":75,"verification":76,"label":6,"fulltextRoute":77,"versionRead":78,"addedByCensus":75},"method",[64,65],"Raul Mur-Artal","Juan D. Tardos","IEEE Transactions on Robotics","journal","IEEE","33(5):1255-1262","10.1109\u002Ftro.2017.2705103","1610.06475","2016-10-20","metadata_verified",[11],false,"confirmed","arXiv","arXiv 1610.06475v2 (2017-06-19), accepted manuscript carrying the IEEE T-RO copyright notice, 9 pages; IEEE Xplore version of record not compared",[80,87,94,98,103,106,112,114],{"category":81,"model":82,"canonical":82,"role":83,"dataset":84,"specs":85,"locator":86},"compute","Intel Core i7-4790","compute for runtime",null,"desktop computer, 16 GB RAM","Sec. IV",{"category":88,"model":89,"canonical":89,"role":90,"dataset":91,"specs":92,"locator":93},"stereo_camera","KITTI stereo camera (model not stated)","dataset sensor","KITTI odometry","baseline about 54 cm, 10 Hz, 1240x376 after rectification","Sec. IV-A",{"category":95,"model":96,"canonical":96,"role":90,"dataset":91,"specs":97,"locator":93},"platform","car (KITTI)","urban and highway driving",{"category":88,"model":99,"canonical":99,"role":90,"dataset":100,"specs":101,"locator":102},"EuRoC stereo camera (model not stated)","EuRoC","baseline about 11 cm, WVGA images at 20 Hz","Sec. IV-B",{"category":95,"model":104,"canonical":104,"role":90,"dataset":100,"specs":105,"locator":102},"micro aerial vehicle (EuRoC)","flights in two rooms and a large industrial environment",{"category":107,"model":108,"canonical":108,"role":109,"dataset":84,"specs":110,"locator":111},"rgbd","Kinect","method input","structured-light projector to infrared camera baseline approximated to 8 cm","Sec. III-A",{"category":107,"model":113,"canonical":113,"role":109,"dataset":84,"specs":110,"locator":111},"Asus Xtion",{"category":107,"model":115,"canonical":115,"role":90,"dataset":116,"specs":117,"locator":118},"TUM RGB-D sensor (model not stated)","TUM RGB-D","640x480 at 30 Hz; freiburg2 depth maps with about 4% scale bias","Sec. IV-C, Table IV",[],{"totalRows":121,"groupCount":122,"groups":123,"others":856},233,33,[124,304,535,799],{"slug":125,"group":126,"sourceId":5,"sourceLabel":6,"table":127,"selfRows":122,"metrics":128,"seqs":141,"entrants":165,"cells":171,"outcomes":298,"locators":299,"hardware":300,"wordings":301,"notes":302},"orbslam2-2017-table-i","orbslam2_2017:Table I","Table I",[129,133,136],{"label":130,"unit":131,"statistic":132,"alignment":44},"trel (%)","%","mean",{"label":134,"unit":135,"statistic":132,"alignment":44},"rrel (deg\u002F100m)","deg\u002F100m",{"label":137,"unit":138,"statistic":139,"alignment":140},"tabs (m), absolute translation RMSE","m","RMSE","not_reported",[142,145,147,149,151,153,155,157,159,161,163],{"dataset":91,"sequence":143,"environment":144},"00","outdoor urban or highway driving",{"dataset":91,"sequence":146,"environment":144},"01",{"dataset":91,"sequence":148,"environment":144},"02",{"dataset":91,"sequence":150,"environment":144},"03",{"dataset":91,"sequence":152,"environment":144},"04",{"dataset":91,"sequence":154,"environment":144},"05",{"dataset":91,"sequence":156,"environment":144},"06",{"dataset":91,"sequence":158,"environment":144},"07",{"dataset":91,"sequence":160,"environment":144},"08",{"dataset":91,"sequence":162,"environment":144},"09",{"dataset":91,"sequence":164,"environment":144},"10",[166,169],{"name":167,"methodId":5,"linkable":168,"proposed":168,"self":168},"ORB-SLAM2 (stereo)",true,{"name":170,"methodId":84,"linkable":75,"proposed":75,"self":75},"Stereo LSD-SLAM",[172,176,179,182,184,186,187,189,191,193,195,197,199,201,203,205,207,208,210,213,215,217,219,221,223,226,228,230,232,234,235,238,240,242,244,245,247,250,252,253,254,255,256,259,260,261,263,265,266,269,271,273,275,276,278,280,282,284,286,287,289,291,292,293,295,297],[173,173,173,174,175,173,175,175,173],0,0.7,-1,[173,177,173,178,175,173,175,175,173],1,0.25,[173,180,173,181,175,173,175,175,173],2,1.3,[177,173,173,183,175,173,175,175,173],0.63,[177,177,173,185,175,173,175,175,173],0.26,[177,180,173,177,175,173,175,175,173],[173,173,177,188,175,173,175,175,173],1.39,[173,177,177,190,175,173,175,175,173],0.21,[173,180,177,192,175,173,175,175,173],10.4,[177,173,177,194,175,173,175,175,173],2.36,[177,177,177,196,175,173,175,175,173],0.36,[177,180,177,198,175,173,175,175,173],9,[173,173,180,200,175,173,175,175,173],0.76,[173,177,180,202,175,173,175,175,173],0.23,[173,180,180,204,175,173,175,175,173],5.7,[177,173,180,206,175,173,175,175,173],0.79,[177,177,180,202,175,173,175,175,173],[177,180,180,209,175,173,175,175,173],2.6,[173,173,211,212,175,173,175,175,173],3,0.71,[173,177,211,214,175,173,175,175,173],0.18,[173,180,211,216,175,173,175,175,173],0.6,[177,173,211,218,175,173,175,175,173],1.01,[177,177,211,220,175,173,175,175,173],0.28,[177,180,211,222,175,173,175,175,173],1.2,[173,173,224,225,175,173,175,175,173],4,0.48,[173,177,224,227,175,173,175,175,173],0.13,[173,180,224,229,175,173,175,175,173],0.2,[177,173,224,231,175,173,175,175,173],0.38,[177,177,224,233,175,173,175,175,173],0.31,[177,180,224,229,175,173,175,175,173],[173,173,236,237,175,173,175,175,173],5,0.4,[173,177,236,239,175,173,175,175,173],0.16,[173,180,236,241,175,173,175,175,173],0.8,[177,173,236,243,175,173,175,175,173],0.64,[177,177,236,214,175,173,175,175,173],[177,180,236,246,175,173,175,175,173],1.5,[173,173,248,249,175,173,175,175,173],6,0.51,[173,177,248,251,175,173,175,175,173],0.15,[173,180,248,241,175,173,175,175,173],[177,173,248,212,175,173,175,175,173],[177,177,248,214,175,173,175,175,173],[177,180,248,181,175,173,175,175,173],[173,173,257,258,175,173,175,175,173],7,0.5,[173,177,257,220,175,173,175,175,173],[173,180,257,258,175,173,175,175,173],[177,173,257,262,175,173,175,175,173],0.56,[177,177,257,264,175,173,175,175,173],0.29,[177,180,257,258,175,173,175,175,173],[173,173,267,268,175,173,175,175,173],8,1.05,[173,177,267,270,175,173,175,175,173],0.32,[173,180,267,272,175,173,175,175,173],3.6,[177,173,267,274,175,173,175,175,173],1.11,[177,177,267,233,175,173,175,175,173],[177,180,267,277,175,173,175,175,173],3.9,[173,173,198,279,175,173,175,175,173],0.87,[173,177,198,281,175,173,175,175,173],0.27,[173,180,198,283,175,173,175,175,173],3.2,[177,173,198,285,175,173,175,175,173],1.14,[177,177,198,178,175,173,175,175,173],[177,180,198,288,175,173,175,175,173],5.6,[173,173,290,216,175,173,175,175,173],10,[173,177,290,281,175,173,175,175,173],[173,180,290,177,175,173,175,175,173],[177,173,290,294,175,173,175,175,173],0.72,[177,177,290,296,175,173,175,175,173],0.33,[177,180,290,246,175,173,175,175,173],[],[127],[],[],[303],"KITTI odometry training sequences, stereo: average relative translation error trel (%) and rotation error rrel (deg\u002F100 m) per the KITTI metric, and absolute translation RMSE tabs (m); ORB-SLAM2 median of 5 runs; Stereo LSD-SLAM values as published by its authors",{"slug":305,"group":306,"sourceId":307,"sourceLabel":308,"table":127,"selfRows":309,"metrics":310,"seqs":313,"entrants":353,"cells":366,"outcomes":527,"locators":530,"hardware":531,"wordings":532,"notes":533},"manhattanslam2021-table-i","manhattanslam2021:Table I","manhattanslam2021","Yunus et al., 2021",18,[311],{"label":312,"unit":138,"statistic":139,"alignment":140},"ATE RMSE (m)",[314,318,320,322,324,326,328,330,332,335,337,339,341,343,345,347,349,351],{"dataset":315,"sequence":316,"environment":317},"ICL-NUIM","lr-kt0","synthetic living room and office",{"dataset":315,"sequence":319,"environment":317},"lr-kt1",{"dataset":315,"sequence":321,"environment":317},"lr-kt2",{"dataset":315,"sequence":323,"environment":317},"lr-kt3",{"dataset":315,"sequence":325,"environment":317},"of-kt0",{"dataset":315,"sequence":327,"environment":317},"of-kt1",{"dataset":315,"sequence":329,"environment":317},"of-kt2",{"dataset":315,"sequence":331,"environment":317},"of-kt3",{"dataset":116,"sequence":333,"environment":334},"fr1\u002Fxyz","real indoor scenes with varying structure and texture, RGB-D camera (carrying mode not stated in the paper)",{"dataset":116,"sequence":336,"environment":334},"fr1\u002Fdesk",{"dataset":116,"sequence":338,"environment":334},"fr2\u002Fxyz",{"dataset":116,"sequence":340,"environment":334},"fr2\u002Fdesk",{"dataset":116,"sequence":342,"environment":334},"fr3\u002Fs-nt-far",{"dataset":116,"sequence":344,"environment":334},"fr3\u002Fs-nt-near",{"dataset":116,"sequence":346,"environment":334},"fr3\u002Fs-t-near",{"dataset":116,"sequence":348,"environment":334},"fr3\u002Fs-t-far",{"dataset":116,"sequence":350,"environment":334},"fr3\u002Fcabinet",{"dataset":116,"sequence":352,"environment":334},"fr3\u002Fl-cabinet",[354,356,358,360,362,364],{"name":355,"methodId":307,"linkable":168,"proposed":168,"self":75},"Ours (ManhattanSLAM)",{"name":357,"methodId":84,"linkable":75,"proposed":75,"self":75},"S-SLAM [11]",{"name":359,"methodId":84,"linkable":75,"proposed":75,"self":75},"RGBD-SLAM [12] (Li et al. 2020)",{"name":361,"methodId":5,"linkable":168,"proposed":75,"self":168},"ORB-SLAM2 [6] (BA and loop closure disabled)",{"name":363,"methodId":84,"linkable":75,"proposed":75,"self":75},"SP-SLAM [5] (BA and loop closure disabled)",{"name":365,"methodId":84,"linkable":75,"proposed":75,"self":75},"L-SLAM [10]",[367,369,370,372,374,376,378,380,382,383,384,385,387,388,390,392,394,396,398,399,401,403,405,407,409,411,412,414,416,418,419,421,422,423,425,426,427,428,429,430,432,433,435,436,438,439,440,441,442,444,445,446,447,448,449,450,451,452,453,454,455,457,458,459,461,462,463,466,467,468,470,471,472,474,476,477,478,479,481,484,485,486,487,489,491,493,494,495,496,497,499,501,502,503,504,505,507,509,510,512,513,514,516,519,520,522,523,525],[173,173,173,368,175,173,175,175,173],0.007,[177,173,173,84,173,173,175,175,173],[180,173,173,371,175,173,175,175,173],0.006,[211,173,173,373,175,173,175,175,173],0.014,[224,173,173,375,175,173,175,175,173],0.019,[236,173,173,377,175,173,175,175,173],0.015,[173,173,177,379,175,173,175,175,173],0.011,[177,173,177,381,175,173,175,175,173],0.016,[180,173,177,377,175,173,175,175,173],[211,173,177,379,175,173,175,175,173],[224,173,177,377,175,173,175,175,173],[236,173,177,386,175,173,175,175,173],0.027,[173,173,180,377,175,173,175,175,173],[177,173,180,389,175,173,175,175,173],0.045,[180,173,180,391,175,173,175,175,173],0.02,[211,173,180,393,175,173,175,175,173],0.021,[224,173,180,395,175,173,175,175,173],0.017,[236,173,180,397,175,173,175,175,173],0.053,[173,173,211,379,175,173,175,175,173],[177,173,211,400,175,173,175,175,173],0.046,[180,173,211,402,175,173,175,175,173],0.012,[211,173,211,404,175,173,175,175,173],0.018,[224,173,211,406,175,173,175,175,173],0.022,[236,173,211,408,175,173,175,175,173],0.143,[173,173,224,410,175,173,175,175,173],0.025,[177,173,224,84,173,173,175,175,173],[180,173,224,413,175,173,175,175,173],0.041,[211,173,224,415,175,173,175,175,173],0.049,[224,173,224,417,175,173,175,175,173],0.031,[236,173,224,391,175,173,175,175,173],[173,173,236,420,175,173,175,175,173],0.013,[177,173,236,84,177,173,175,175,173],[180,173,236,391,175,173,175,175,173],[211,173,236,424,175,173,175,175,173],0.029,[224,173,236,404,175,173,175,175,173],[236,173,236,377,175,173,175,175,173],[173,173,248,377,175,173,175,175,173],[177,173,248,417,175,173,175,175,173],[180,173,248,379,175,173,175,175,173],[211,173,248,431,175,173,175,175,173],0.03,[224,173,248,386,175,173,175,175,173],[236,173,248,434,175,173,175,175,173],0.026,[173,173,257,420,175,173,175,175,173],[177,173,257,437,175,173,175,175,173],0.065,[180,173,257,373,175,173,175,175,173],[211,173,257,402,175,173,175,175,173],[224,173,257,402,175,173,175,175,173],[236,173,257,379,175,173,175,175,173],[173,173,267,443,175,173,175,175,173],0.01,[177,173,267,84,177,173,175,175,173],[180,173,267,84,177,173,175,175,173],[211,173,267,443,175,173,175,175,173],[224,173,267,443,175,173,175,175,173],[236,173,267,84,173,173,175,175,173],[173,173,198,386,175,173,175,175,173],[177,173,198,84,177,173,175,175,173],[180,173,198,84,177,173,175,175,173],[211,173,198,406,175,173,175,175,173],[224,173,198,434,175,173,175,175,173],[236,173,198,84,173,173,175,175,173],[173,173,290,456,175,173,175,175,173],0.008,[177,173,290,84,177,173,175,175,173],[180,173,290,84,177,173,175,175,173],[211,173,290,460,175,173,175,175,173],0.009,[224,173,290,460,175,173,175,175,173],[236,173,290,84,173,173,175,175,173],[173,173,464,465,175,173,175,175,173],11,0.037,[177,173,464,84,177,173,175,175,173],[180,173,464,84,177,173,175,175,173],[211,173,464,469,175,173,175,175,173],0.04,[224,173,464,410,175,173,175,175,173],[236,173,464,84,173,173,175,175,173],[173,173,473,469,175,173,175,175,173],12,[177,173,473,475,175,173,175,175,173],0.281,[180,173,473,406,175,173,175,175,173],[211,173,473,84,177,173,175,175,173],[224,173,473,417,175,173,175,175,173],[236,173,473,480,175,173,175,175,173],0.141,[173,173,482,483,175,173,175,175,173],13,0.023,[177,173,482,437,175,173,175,175,173],[180,173,482,410,175,173,175,175,173],[211,173,482,84,177,173,175,175,173],[224,173,482,488,175,173,175,175,173],0.024,[236,173,482,490,175,173,175,175,173],0.066,[173,173,492,402,175,173,175,175,173],14,[177,173,492,373,175,173,175,175,173],[180,173,492,84,173,173,175,175,173],[211,173,492,379,175,173,175,175,173],[224,173,492,443,175,173,175,175,173],[236,173,492,498,175,173,175,175,173],0.156,[173,173,500,406,175,173,175,175,173],15,[177,173,500,373,175,173,175,175,173],[180,173,500,84,173,173,175,175,173],[211,173,500,379,175,173,175,175,173],[224,173,500,381,175,173,175,175,173],[236,173,500,506,175,173,175,175,173],0.212,[173,173,508,483,175,173,175,175,173],16,[177,173,508,84,173,173,175,175,173],[180,173,508,511,175,173,175,175,173],0.035,[211,173,508,84,177,173,175,175,173],[224,173,508,84,177,173,175,175,173],[236,173,508,515,175,173,175,175,173],0.291,[173,173,517,518,175,173,175,175,173],17,0.083,[177,173,517,84,173,173,175,175,173],[180,173,517,521,175,173,175,175,173],0.071,[211,173,517,84,177,173,175,175,173],[224,173,517,524,175,173,175,175,173],0.074,[236,173,517,526,175,173,175,175,173],0.14,[528,529],"result not available","tracking failure",[127],[],[],[534],"Translation ATE RMSE (m); ORB-SLAM2 and SP-SLAM run without bundle adjustment and loop closure for fairness; 'x' tracking failure, '-' result not available; the number of frames using Manhattan-frame tracking is also listed in the table (not extracted)",{"slug":536,"group":537,"sourceId":538,"sourceLabel":539,"table":540,"selfRows":482,"metrics":541,"seqs":546,"entrants":575,"cells":594,"outcomes":789,"locators":791,"hardware":793,"wordings":795,"notes":796},"dpvslam2024-table-2b","dpvslam2024:Table 2b","dpvslam2024","Lipson et al., 2024","Table 2b",[542,544],{"label":543,"unit":138,"statistic":140,"alignment":140},"ATE[m]",{"label":545,"unit":545,"statistic":132,"alignment":44},"FPS",[547,551,553,555,557,559,561,563,565,567,569,571,573],{"dataset":548,"sequence":549,"environment":550},"KITTI","seq 00","outdoor urban driving",{"dataset":548,"sequence":552,"environment":550},"seq 01",{"dataset":548,"sequence":554,"environment":550},"seq 02",{"dataset":548,"sequence":556,"environment":550},"seq 03",{"dataset":548,"sequence":558,"environment":550},"seq 04",{"dataset":548,"sequence":560,"environment":550},"seq 05",{"dataset":548,"sequence":562,"environment":550},"seq 06",{"dataset":548,"sequence":564,"environment":550},"seq 07",{"dataset":548,"sequence":566,"environment":550},"seq 08",{"dataset":548,"sequence":568,"environment":550},"seq 09",{"dataset":548,"sequence":570,"environment":550},"seq 10",{"dataset":548,"sequence":572,"environment":550},"average of 11 sequences",{"dataset":548,"sequence":574,"environment":550},"sequences 00-10",[576,578,581,583,586,588,590,592],{"name":577,"methodId":5,"linkable":168,"proposed":75,"self":168},"ORB-SLAM2 [ 18 ]",{"name":579,"methodId":580,"linkable":168,"proposed":75,"self":75},"ORB-SLAM3 [ 2 ]","orbslam3_2021",{"name":582,"methodId":84,"linkable":75,"proposed":75,"self":75},"LDSO [ 11 ]",{"name":584,"methodId":585,"linkable":168,"proposed":75,"self":75},"DROID-VO [ 31 ]","droidslam2021",{"name":587,"methodId":84,"linkable":75,"proposed":75,"self":75},"DPVO [ 32 ]",{"name":589,"methodId":585,"linkable":168,"proposed":75,"self":75},"DROID-SLAM [ 31 ]",{"name":591,"methodId":84,"linkable":75,"proposed":168,"self":75},"DPV-SLAM",{"name":593,"methodId":84,"linkable":75,"proposed":168,"self":75},"DPV-SLAM++",[595,597,598,600,602,604,606,608,610,612,614,616,617,619,621,622,624,626,628,630,632,634,636,638,640,641,642,644,646,648,650,652,654,656,658,660,662,664,666,668,670,672,674,676,677,679,681,683,685,687,689,691,692,694,696,698,700,702,704,706,708,710,712,714,716,718,720,722,723,725,726,728,730,732,734,735,737,738,739,741,743,745,747,749,751,753,755,757,759,761,763,765,767,769,771,772,774,776,778,780,782,784,786,788],[173,173,173,596,175,173,175,175,173],8.27,[173,173,177,84,173,173,175,175,173],[173,173,180,599,175,173,175,175,173],26.86,[173,173,211,601,175,173,175,175,173],1.21,[173,173,224,603,175,173,175,175,173],0.77,[173,173,236,605,175,173,175,175,173],7.91,[173,173,248,607,175,173,175,175,173],12.54,[173,173,257,609,175,173,175,175,173],3.44,[173,173,267,611,175,173,175,175,173],46.81,[173,173,198,613,175,173,175,175,173],76.54,[173,173,290,615,175,173,175,175,173],6.61,[173,173,464,84,177,173,175,175,173],[173,177,473,618,175,173,173,175,177],34,[177,173,173,620,175,173,175,175,173],6.77,[177,173,177,84,173,173,175,175,173],[177,173,180,623,175,173,175,175,173],30.5,[177,173,211,625,175,173,175,175,173],1.036,[177,173,224,627,175,173,175,175,173],0.93,[177,173,236,629,175,173,175,175,173],5.542,[177,173,248,631,175,173,175,175,173],16.605,[177,173,257,633,175,173,175,175,173],9.7,[177,173,267,635,175,173,175,175,173],60.687,[177,173,198,637,175,173,175,175,173],7.899,[177,173,290,639,175,173,175,175,173],8.65,[177,173,464,84,177,173,175,175,173],[177,177,473,618,175,173,173,175,177],[180,173,173,643,175,173,175,175,173],9.32,[180,173,177,645,175,173,175,175,173],11.68,[180,173,180,647,175,173,175,175,173],31.98,[180,173,211,649,175,173,175,175,173],2.85,[180,173,224,651,175,173,175,175,173],1.22,[180,173,236,653,175,173,175,175,173],5.1,[180,173,248,655,175,173,175,175,173],13.55,[180,173,257,657,175,173,175,175,173],2.96,[180,173,267,659,175,173,175,175,173],129.02,[180,173,198,661,175,173,175,175,173],21.64,[180,173,290,663,175,173,175,175,173],17.36,[180,173,464,665,175,173,175,175,173],22.42,[180,177,473,667,175,173,173,175,177],49,[211,173,173,669,175,173,175,175,173],98.43,[211,173,177,671,175,173,175,175,173],84.2,[211,173,180,673,175,173,175,175,173],108.8,[211,173,211,675,175,173,175,175,173],2.58,[211,173,224,627,175,173,175,175,173],[211,173,236,678,175,173,175,175,173],59.27,[211,173,248,680,175,173,175,175,173],64.4,[211,173,257,682,175,173,175,175,173],24.2,[211,173,267,684,175,173,175,175,173],64.55,[211,173,198,686,175,173,175,175,173],71.8,[211,173,290,688,175,173,175,175,173],16.91,[211,173,464,690,175,173,175,175,173],54.19,[211,177,473,517,175,173,173,175,177],[224,173,173,693,175,173,175,175,173],113.21,[224,173,177,695,175,173,175,175,173],12.69,[224,173,180,697,175,173,175,175,173],123.4,[224,173,211,699,175,173,175,175,173],2.09,[224,173,224,701,175,173,175,175,173],0.68,[224,173,236,703,175,173,175,175,173],58.96,[224,173,248,705,175,173,175,175,173],54.78,[224,173,257,707,175,173,175,175,173],19.26,[224,173,267,709,175,173,175,175,173],115.9,[224,173,198,711,175,173,175,175,173],75.1,[224,173,290,713,175,173,175,175,173],13.63,[224,173,464,715,175,173,175,175,173],53.61,[224,177,473,717,175,173,173,175,177],48,[236,173,173,719,175,173,175,175,173],92.1,[236,173,177,721,175,173,175,175,173],344.6,[236,173,180,84,173,173,175,175,173],[236,173,211,724,175,173,175,175,173],2.38,[236,173,224,177,175,173,175,175,173],[236,173,236,727,175,173,175,175,173],118.5,[236,173,248,729,175,173,175,175,173],62.47,[236,173,257,731,175,173,175,175,173],21.78,[236,173,267,733,175,173,175,175,173],161.6,[236,173,198,84,173,173,175,175,173],[236,173,290,736,175,173,175,175,173],118.7,[236,173,464,84,177,173,175,175,173],[236,177,473,517,175,173,173,175,177],[248,173,173,740,175,173,175,175,173],112.8,[248,173,177,742,175,173,175,175,173],11.5,[248,173,180,744,175,173,175,175,173],123.53,[248,173,211,746,175,173,175,175,173],2.5,[248,173,224,748,175,173,175,175,173],0.81,[248,173,236,750,175,173,175,175,173],57.8,[248,173,248,752,175,173,175,175,173],54.86,[248,173,257,754,175,173,175,175,173],18.77,[248,173,267,756,175,173,175,175,173],110.49,[248,173,198,758,175,173,175,175,173],76.66,[248,173,290,760,175,173,175,175,173],13.65,[248,173,464,762,175,173,175,175,173],53.03,[248,177,473,764,175,173,173,175,177],39,[257,173,173,766,175,173,175,175,173],8.3,[257,173,177,768,175,173,175,175,173],11.86,[257,173,180,770,175,173,175,175,173],39.64,[257,173,211,746,175,173,175,175,173],[257,173,224,773,175,173,175,175,173],0.78,[257,173,236,775,175,173,175,175,173],5.74,[257,173,248,777,175,173,175,175,173],11.6,[257,173,257,779,175,173,175,175,173],1.52,[257,173,267,781,175,173,175,175,173],110.9,[257,173,198,783,175,173,175,175,173],76.7,[257,173,290,785,175,173,175,175,173],13.7,[257,173,464,787,175,173,175,175,173],25.76,[257,177,473,764,175,173,173,175,177],[790,140],"failed",[792],"Table 2(b)",[794],"NVIDIA RTX 3090 (all timing experiments, Sec. 4)",[],[797,798],"KITTI odometry sequences 00-10, monocular ATE; X = failure, '-' = average not computed; values checked against the ECCV 2024 version of record (same table numbering)","KITTI odometry sequences 00-10, monocular; FPS column; values checked against the ECCV 2024 version of record (same table numbering)",{"slug":800,"group":801,"sourceId":5,"sourceLabel":6,"table":802,"selfRows":473,"metrics":803,"seqs":813,"entrants":822,"cells":824,"outcomes":849,"locators":850,"hardware":851,"wordings":853,"notes":854},"orbslam2-2017-table-iv","orbslam2_2017:Table IV","Table IV",[804,807,809,811],{"label":805,"unit":806,"statistic":132,"alignment":44},"Tracking total per frame (mean)","ms",{"label":808,"unit":806,"statistic":132,"alignment":44},"Local mapping total per keyframe (mean)",{"label":810,"unit":806,"statistic":140,"alignment":44},"Loop closing total (single loop)",{"label":812,"unit":806,"statistic":140,"alignment":44},"Full BA total incl. map update (single loop)",[814,817,819],{"dataset":100,"sequence":815,"environment":816},"V2_02","indoor room, MAV; stereo 752x480, 20 Hz, 1000 ORB features",{"dataset":91,"sequence":158,"environment":818},"outdoor urban driving; stereo 1226x370, 10 Hz, 2000 ORB features",{"dataset":116,"sequence":820,"environment":821},"fr3_office","indoor (TUM RGB-D); RGB-D 640x480, 30 Hz, 1000 ORB features",[823],{"name":7,"methodId":5,"linkable":168,"proposed":168,"self":168},[825,827,829,831,833,835,837,839,841,843,845,847],[173,173,173,826,175,173,173,175,173],41.66,[173,177,173,828,175,173,173,175,173],174.1,[173,180,173,830,175,173,173,175,173],108.59,[173,211,173,832,175,173,173,175,173],396.02,[173,173,177,834,175,173,173,175,173],49.47,[173,177,177,836,175,173,173,175,173],129.52,[173,180,177,838,175,173,173,175,173],284.88,[173,211,177,840,175,173,173,175,173],1205.78,[173,173,180,842,175,173,173,175,173],25.58,[173,177,180,844,175,173,173,175,173],267.33,[173,180,180,846,175,173,173,175,173],598.7,[173,211,180,848,175,173,173,175,173],1793.02,[],[802],[852],"Intel Core i7-4790, 16 GB RAM",[],[855],"Mean time per thread task (ms, mean of the thread total); loop and full-BA values are single measurements because each sequence has one loop; component times not transcribed",[857,863,869,875,879,885,892,899,905,910,914,920,927,932,940,947,952,957,961,966,971,976,981,987,992,998,1003,1007,1012],{"group":858,"slug":859,"sourceLabel":860,"table":861,"selfRows":473,"datasets":862},"orbslam3_2021:Table II","orbslam3-2021-table-ii","Campos et al., 2021","Table II",[100],{"group":864,"slug":865,"sourceLabel":866,"table":127,"selfRows":473,"datasets":867},"rogers2020subttunnel:Table I","rogers2020subttunnel-table-i","Rogers et al., 2020",[868],"SubT-Tunnel",{"group":870,"slug":871,"sourceLabel":872,"table":127,"selfRows":464,"datasets":873},"ldso2018:Table I","ldso2018-table-i","Gao et al., 2018",[874],"KITTI Odometry",{"group":876,"slug":877,"sourceLabel":6,"table":861,"selfRows":464,"datasets":878},"orbslam2_2017:Table II","orbslam2-2017-table-ii",[100],{"group":880,"slug":881,"sourceLabel":882,"table":883,"selfRows":290,"datasets":884},"droidslam2021:Table 4","droidslam2021-table-4","Teed & Deng, 2021","Table 4",[116],{"group":886,"slug":887,"sourceLabel":888,"table":889,"selfRows":198,"datasets":890},"yan2026_underground3dgsslam:Table III","yan2026-underground3dgsslam-table-iii","Yan et al., 2026b","Table III",[891],"Underground_RGB-D (authors' field test dataset)",{"group":893,"slug":894,"sourceLabel":895,"table":896,"selfRows":267,"datasets":897},"badslam2019:Table 3","badslam2019-table-3","Schöps et al., 2019","Table 3",[898],"synthetic TUM RGB-D renders (7 datasets per category)",{"group":900,"slug":901,"sourceLabel":902,"table":903,"selfRows":267,"datasets":904},"monogs2024:Table 1","monogs2024-table-1","Matsuki et al., 2024","Table 1",[116],{"group":906,"slug":907,"sourceLabel":908,"table":883,"selfRows":257,"datasets":909},"d3vo2020:Table 4","d3vo2020-table-4","Yang et al., 2020a",[91],{"group":911,"slug":912,"sourceLabel":6,"table":889,"selfRows":257,"datasets":913},"orbslam2_2017:Table III","orbslam2-2017-table-iii",[116],{"group":915,"slug":916,"sourceLabel":917,"table":861,"selfRows":248,"datasets":918},"camvox2021:Table II","camvox2021-table-ii","Zhu et al., 2021",[919,116],"SUSTech dataset (CamVox)",{"group":921,"slug":922,"sourceLabel":923,"table":924,"selfRows":248,"datasets":925},"loopyslam2024:Table 2","loopyslam2024-table-2","Liso et al., 2024","Table 2",[926],"TUM-RGBD",{"group":928,"slug":929,"sourceLabel":930,"table":896,"selfRows":248,"datasets":931},"pointslam2023:Table 3","pointslam2023-table-3","Sandström et al., 2023",[926],{"group":933,"slug":934,"sourceLabel":935,"table":903,"selfRows":248,"datasets":936},"splatam2024:Table 1","splatam2024-table-1","Keetha et al., 2024",[937,938,939,926],"Replica","ScanNet (original)","ScanNet++",{"group":941,"slug":942,"sourceLabel":943,"table":944,"selfRows":224,"datasets":945},"chen2025quadrupedinspection:Table 7","chen2025quadrupedinspection-table-7","Chen et al., 2025a","Table 7",[946],"authors' HKUST corridor recording (ROS bag)",{"group":948,"slug":949,"sourceLabel":950,"table":924,"selfRows":224,"datasets":951},"gsslam2024:Table 2","gsslam2024-table-2","Yan et al., 2024",[116],{"group":953,"slug":954,"sourceLabel":955,"table":924,"selfRows":224,"datasets":956},"rtgslam2024:Table 2","rtgslam2024-table-2","Peng et al., 2024",[116],{"group":958,"slug":959,"sourceLabel":895,"table":924,"selfRows":211,"datasets":960},"badslam2019:Table 2","badslam2019-table-2",[116],{"group":962,"slug":963,"sourceLabel":964,"table":883,"selfRows":211,"datasets":965},"coslam2023:Table 4","coslam2023-table-4","Wang et al., 2023a",[116],{"group":967,"slug":968,"sourceLabel":969,"table":896,"selfRows":211,"datasets":970},"imap2021:Table 3","imap2021-table-3","Sucar et al., 2021",[116],{"group":972,"slug":973,"sourceLabel":974,"table":924,"selfRows":211,"datasets":975},"niceslam2022:Table 2","niceslam2022-table-2","Zhu et al., 2022a",[116],{"group":977,"slug":978,"sourceLabel":888,"table":979,"selfRows":211,"datasets":980},"yan2026_underground3dgsslam:Table VI","yan2026-underground3dgsslam-table-vi","Table VI",[116],{"group":982,"slug":983,"sourceLabel":882,"table":984,"selfRows":180,"datasets":985},"droidslam2021:Fig. 4 table","droidslam2021-fig-4-table","Fig. 4 table",[986],"ETH3D SLAM benchmark",{"group":988,"slug":989,"sourceLabel":308,"table":861,"selfRows":180,"datasets":990},"manhattanslam2021:Table II","manhattanslam2021-table-ii",[991],"TAMU RGB-D",{"group":993,"slug":994,"sourceLabel":995,"table":984,"selfRows":180,"datasets":996},"openvslam2019:Fig. 4 table","openvslam2019-fig-4-table","Sumikura et al., 2019",[997],"EuRoC MAV",{"group":999,"slug":1000,"sourceLabel":995,"table":1001,"selfRows":180,"datasets":1002},"openvslam2019:Fig. 6 table","openvslam2019-fig-6-table","Fig. 6 table",[874],{"group":1004,"slug":1005,"sourceLabel":539,"table":903,"selfRows":177,"datasets":1006},"dpvslam2024:Table 1","dpvslam2024-table-1",[116],{"group":1008,"slug":1009,"sourceLabel":882,"table":1010,"selfRows":177,"datasets":1011},"droidslam2021:Table 5","droidslam2021-table-5","Table 5",[997],{"group":1013,"slug":1014,"sourceLabel":860,"table":979,"selfRows":177,"datasets":1015},"orbslam3_2021:Table VI","orbslam3-2021-table-vi",[100],1790510655392]