[{"data":1,"prerenderedAt":949},["ShallowReactive",2],{"method-orbslam3_2021":3},{"method":4,"reference":61,"equipment":83,"figures":115,"results":116},{"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":24,"sensors":33,"platform":38,"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},"orbslam3_2021","Campos et al., 2021","ORB-SLAM3","ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial, and Multimap SLAM",2021,"recent","C08","full_slam_with_global_correction","ORB-SLAM3 在 ORB-SLAM2 基礎上加入緊耦合的視覺慣性（visual-inertial）最大後驗估計，包括 IMU 初始化階段，並支援針孔與魚眼相機。其 Atlas 多地圖機制在追蹤失敗時另起新地圖，重訪時再以改良召回率的場所辨識（place recognition）將地圖合併，使 BA 可使用時間上相隔很遠甚至跨作業階段的共視關鍵影格。系統輸出仍是稀疏地圖點與關鍵影格軌跡。","ORB-SLAM3 adds tightly integrated MAP visual-inertial estimation (including IMU initialisation), fisheye support and an Atlas multi-map with map merging, reusing co-visible keyframes across time and sessions in BA.","full_text_reviewed","peer_reviewed_published","main_body","論文未報告營建工地測試；評估資料為 EuRoC（含工業廠房）與 TUM-VI。作者指出低紋理環境為主要失效情境，與施工中大面積素面牆體的條件相關，但本文尚未找到直接工地驗證（推論）。",[20],"public_benchmark",[22,23],"Stereo-inertial average accuracy 3.5 cm on EuRoC and 9 mm under quick hand-held motion in TUM-VI room sequences (abstract)","Survives long periods of poor visual information by starting and later merging maps (abstract)",[25,26,27,28,29,30,31,32],"Main failure case is low-texture environments (Sec. VIII)","IMU is difficult to initialise with slow motion or without roll\u002Fpitch excitation, e.g. a car on flat ground (Sec. VIII)","Monocular-inertial cannot estimate depth under pure rotation during exploration (Sec. VIII)","Long outdoor TUM-VI sequences: scarce close features let inertial parameters (scale, accelerometer bias) drift, giving errors of 10 to 70 m; points beyond 20 m were discarded outdoors to suppress sky features (Sec. VII-B)","Monocular ORB-SLAM3 did not complete V203 in single-session EuRoC (Table II)","Stereo-inertial was less accurate than monocular-inertial in two Machine Hall sequences, attributed to greater scene depth (Sec. VII-A)","In some dark TUM-VI slide sequences VINS-Mono and BASALT, which track with Lucas-Kanade, were more accurate (Sec. VII-B)","A visual-inertial map lost within 15 s of IMU initialisation is discarded (Sec. V-D)",[34,35,36,37],"monocular camera","stereo (pin-hole or fisheye; rectification not required)","RGB-D (supported by the library; no RGB-D experiment reported)","IMU",[39,40],"UAV","handheld","Keyframe-based MAP estimation: visual or visual-inertial BA with IMU preintegration on manifold and Huber-robust reprojection terms; tracking optimises only the states of the last two frames with map points fixed; local mapping optimises a sliding window of keyframes and their points with covisible keyframes fixed. IMU initialisation in three MAP steps: 2 s of monocular visual-only BA (10 keyframes at 4 Hz), inertial-only MAP for scale, gravity direction, biases and velocities with a bias prior, then joint visual-inertial MAP; visual-inertial BA again 5 and 15 s after initialisation (scale error about 5% after 2 s and 1% after 15 s)","ORB features and reprojection; DBoW2 keyframe database with a new place-recognition method of improved recall (Sec. III; abstract)","discrete keyframe states; IMU residuals between frames in visual-inertial mode (Sec. III)","not_applicable","For each new keyframe, DBoW2 returns the three most similar Atlas keyframes not covisible with it; for each candidate a local window (candidate plus best covisible keyframes) is aligned by RANSAC with Horn's method on 3D-3D matches (Sim(3) for monocular or immature monocular-inertial maps, SE(3) otherwise), refined by guided matching and bidirectional reprojection optimisation, and verified in three covisible keyframes already in the map instead of three consecutive BoW detections; mature visual-inertial maps also require pitch and roll below a threshold. A match in the active map triggers loop correction, a match in another map triggers map merging","Loop: welding window with point fusion, essential-graph pose-graph optimisation, then global BA in an independent thread; in the visual-inertial case global BA runs only if the number of keyframes is below a threshold. Map merge: welding BA over the merge window (stored-map keyframes outside it fixed) followed by essential-graph optimisation of the whole merged map with the welding area fixed. IMU scale and gravity refinement every 10 s until 100 keyframes or 75 s after initialisation","Atlas of disconnected sparse maps (map points plus keyframes), one active (Sec. III)","No prior map required; maps of earlier sessions stored in the Atlas can be reused and merged. Requires camera intrinsics, body-to-camera extrinsics T_CB from calibration and, for stereo, a constant relative SE(3) between the cameras; IMU initialisation uses a prior that keeps biases near zero","Keyframe trajectories and sparse map points (on EuRoC V202 the four ORB-SLAM3 configurations keep 9,686 to 14,245 map points and 135 to 332 keyframes, Table VI); no dense reconstruction is produced or evaluated in the paper","Intel Core i7-7700 CPU at 3.6 GHz with 32 GB memory, CPU only; real time at 30 to 40 frames and 3 to 6 keyframes per second. On EuRoC V202 the mean tracking time is 21.52 ms (monocular), 31.48 ms (stereo), 23.22 ms (monocular-inertial) and 33.05 ms (stereo-inertial) against 37.87 ms for ORB-SLAM2 stereo (Table VI). In the V201 to V203 multi-session run (Table VII), place recognition totals 3.45 to 5.89 ms per keyframe, map merging 120.63 to 287.33 ms, and the loop full BA up to 4134.94 ms in a separate thread","https:\u002F\u002Fgithub.com\u002FUZ-SLAMLab\u002FORB_SLAM3","GPLv3 (LICENSE file)",[54,58],{"relation":55,"title":56,"doi_or_url":57},"preprint","ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM (arXiv)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2007.11898",{"relation":59,"title":60,"doi_or_url":51},"code_release","ORB_SLAM3",{"id":5,"kind":62,"shortName":7,"title":63,"authors":64,"year":9,"venue":70,"venueType":71,"publisher":72,"volumeIssuePages":73,"doi":74,"arxivId":75,"url":57,"firstPublicDate":76,"publicationStatus":16,"metadataStatus":77,"fulltextStatus":15,"era":10,"classicReason":44,"codeUrl":51,"cluster":11,"topics":78,"mdpi":79,"verification":80,"label":6,"fulltextRoute":81,"versionRead":82,"addedByCensus":79},"method","ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual–Inertial, and Multimap SLAM",[65,66,67,68,69],"Carlos Campos","Richard Elvira","Juan J. Gomez Rodriguez","Jose M. M. Montiel","Juan D. Tardos","IEEE Transactions on Robotics","journal","IEEE","37(6):1874-1890","10.1109\u002Ftro.2021.3075644","2007.11898","2020-07-23","metadata_verified",[11],false,"confirmed","arXiv","arXiv 2007.11898v2 (2021-04-23), accepted manuscript carrying the IEEE T-RO copyright notice, 18 pages; IEEE Xplore version of record (free to read, bronze OA per OpenAlex) not compared",[84,91,98,102,107,112],{"category":85,"model":86,"canonical":86,"role":87,"dataset":88,"specs":89,"locator":90},"compute","Intel Core i7-7700","compute for runtime",null,"3.6 GHz, 32 GB memory, CPU only","Sec. VII",{"category":92,"model":93,"canonical":93,"role":94,"dataset":95,"specs":96,"locator":97},"stereo_camera","EuRoC stereo camera (model not stated)","dataset sensor","EuRoC","752x480 at 20 Hz; 1000 to 1200 ORB features per image in the experiments","Table VI",{"category":99,"model":100,"canonical":100,"role":94,"dataset":95,"specs":101,"locator":97},"imu","EuRoC IMU (model not stated)","200 Hz",{"category":103,"model":104,"canonical":104,"role":94,"dataset":95,"specs":105,"locator":106},"platform","drone (EuRoC micro aerial vehicle)","11 sequences in a machine hall and two Vicon rooms","Abstract; Sec. VII-C",{"category":92,"model":108,"canonical":108,"role":94,"dataset":109,"specs":110,"locator":111},"TUM-VI hand-held fisheye stereo-inertial rig, cameras (model not stated)","TUM-VI","fisheye stereo; CLAHE equalisation applied; 1500 ORB points per image (monocular-inertial) or 1000 (stereo-inertial)","Sec. VII-B",{"category":99,"model":113,"canonical":113,"role":94,"dataset":109,"specs":114,"locator":111},"TUM-VI rig IMU (model not stated)","part of the hand-held stereo-inertial rig",[],{"totalRows":117,"groupCount":118,"groups":119,"others":740},294,42,[120,279,361,683],{"slug":121,"group":122,"sourceId":5,"sourceLabel":6,"table":123,"selfRows":124,"metrics":125,"seqs":137,"entrants":165,"cells":175,"outcomes":271,"locators":274,"hardware":275,"wordings":276,"notes":277},"orbslam3-2021-table-ii","orbslam3_2021:Table II","Table II",48,[126,131,134,136],{"label":127,"unit":128,"statistic":129,"alignment":130},"RMS ATE (m)","m","RMSE","Sim3",{"label":132,"unit":128,"statistic":133,"alignment":130},"RMS ATE (m), Avg column","mean",{"label":127,"unit":128,"statistic":129,"alignment":135},"SE3",{"label":132,"unit":128,"statistic":133,"alignment":135},[138,141,143,145,147,149,152,154,156,158,160,162],{"dataset":95,"sequence":139,"environment":140},"MH01","machine hall, drone",{"dataset":95,"sequence":142,"environment":140},"MH02",{"dataset":95,"sequence":144,"environment":140},"MH03",{"dataset":95,"sequence":146,"environment":140},"MH04",{"dataset":95,"sequence":148,"environment":140},"MH05",{"dataset":95,"sequence":150,"environment":151},"V101","indoor Vicon room, drone",{"dataset":95,"sequence":153,"environment":151},"V102",{"dataset":95,"sequence":155,"environment":151},"V103",{"dataset":95,"sequence":157,"environment":151},"V201",{"dataset":95,"sequence":159,"environment":151},"V202",{"dataset":95,"sequence":161,"environment":151},"V203",{"dataset":95,"sequence":163,"environment":164},"average over the 11 sequences","machine hall and Vicon rooms, drone",[166,169,171,173],{"name":167,"methodId":5,"linkable":168,"proposed":168,"self":168},"ORB-SLAM3 (monocular)",true,{"name":170,"methodId":5,"linkable":168,"proposed":168,"self":168},"ORB-SLAM3 (stereo)",{"name":172,"methodId":5,"linkable":168,"proposed":168,"self":168},"ORB-SLAM3 (monocular-inertial)",{"name":174,"methodId":5,"linkable":168,"proposed":168,"self":168},"ORB-SLAM3 (stereo-inertial)",[176,180,183,186,189,192,195,198,200,203,206,208,211,212,214,216,218,220,222,224,226,227,228,230,232,234,236,238,240,242,244,245,246,248,250,251,253,255,256,257,259,261,263,265,266,268,269,270],[177,177,177,178,179,177,179,179,177],0,0.016,-1,[177,177,181,182,179,177,179,179,177],1,0.027,[177,177,184,185,179,177,179,179,177],2,0.028,[177,177,187,188,179,177,179,179,177],3,0.138,[177,177,190,191,179,177,179,179,177],4,0.072,[177,177,193,194,179,177,179,179,177],5,0.033,[177,177,196,197,179,177,179,179,177],6,0.015,[177,177,199,194,179,177,179,179,177],7,[177,177,201,202,179,177,179,179,177],8,0.023,[177,177,204,205,179,177,179,179,177],9,0.029,[177,177,207,88,177,177,179,179,177],10,[177,181,209,210,181,177,179,179,177],11,0.041,[181,184,177,205,179,177,179,179,177],[181,184,181,213,179,177,179,179,177],0.019,[181,184,184,215,179,177,179,179,177],0.024,[181,184,187,217,179,177,179,179,177],0.085,[181,184,190,219,179,177,179,179,177],0.052,[181,184,193,221,179,177,179,179,177],0.035,[181,184,196,223,179,177,179,179,177],0.025,[181,184,199,225,179,177,179,179,177],0.061,[181,184,201,210,179,177,179,179,177],[181,184,204,185,179,177,179,179,177],[181,184,207,229,179,177,179,179,177],0.521,[181,187,209,231,179,177,179,179,177],0.084,[184,184,177,233,179,177,179,179,177],0.062,[184,184,181,235,179,177,179,179,177],0.037,[184,184,184,237,179,177,179,179,177],0.046,[184,184,187,239,179,177,179,179,177],0.075,[184,184,190,241,179,177,179,179,177],0.057,[184,184,193,243,179,177,179,179,177],0.049,[184,184,196,197,179,177,179,179,177],[184,184,199,235,179,177,179,179,177],[184,184,201,247,179,177,179,179,177],0.042,[184,184,204,249,179,177,179,179,177],0.021,[184,184,207,182,179,177,179,179,177],[184,187,209,252,179,177,179,179,177],0.043,[187,184,177,254,179,177,179,179,177],0.036,[187,184,181,194,179,177,179,179,177],[187,184,184,221,179,177,179,179,177],[187,184,187,258,179,177,179,179,177],0.051,[187,184,190,260,179,177,179,179,177],0.082,[187,184,193,262,179,177,179,179,177],0.038,[187,184,196,264,179,177,179,179,177],0.014,[187,184,199,215,179,177,179,179,177],[187,184,201,267,179,177,179,179,177],0.032,[187,184,204,264,179,177,179,179,177],[187,184,207,215,179,177,179,179,177],[187,187,209,221,179,177,179,179,177],[272,273],"failed (sequence not completed, '-' in table)","average over completed sequences only (system did not complete all sequences, marked *)",[123],[],[],[278],"EuRoC single session, RMS ATE (m); ORB-SLAM3 median of 10 executions, Sim(3) alignment for monocular and SE(3) otherwise; other systems as reported by their authors except VINS-Mono and VINS-Fusion (run by the ORB-SLAM3 authors with default settings) and MCSKF, OKVIS, ROVIO (values from ref. [78]); ORB-SLAM, ORBSLAM-VI and BASALT use keyframe trajectories, ORB-SLAM and ORBSLAM-VI raw ground truth. Row cap: per-sequence values kept only for ORB-SLAM3, ORB-SLAM2, VINS-Mono and OKVIS; averages kept for all systems",{"slug":280,"group":281,"sourceId":5,"sourceLabel":6,"table":282,"selfRows":283,"metrics":284,"seqs":289,"entrants":305,"cells":310,"outcomes":355,"locators":356,"hardware":357,"wordings":358,"notes":359},"orbslam3-2021-table-iv","orbslam3_2021:Table IV","Table IV",28,[285,286,287,288],{"label":127,"unit":128,"statistic":129,"alignment":130},{"label":127,"unit":128,"statistic":129,"alignment":135},{"label":127,"unit":128,"statistic":133,"alignment":130},{"label":127,"unit":128,"statistic":133,"alignment":135},[290,293,295,297,299,301,303],{"dataset":109,"sequence":291,"environment":292},"room1","indoor room, hand-held fisheye rig",{"dataset":109,"sequence":294,"environment":292},"room2",{"dataset":109,"sequence":296,"environment":292},"room3",{"dataset":109,"sequence":298,"environment":292},"room4",{"dataset":109,"sequence":300,"environment":292},"room5",{"dataset":109,"sequence":302,"environment":292},"room6",{"dataset":109,"sequence":304,"environment":292},"average (Avg.)",[306,307,308,309],{"name":167,"methodId":5,"linkable":168,"proposed":168,"self":168},{"name":170,"methodId":5,"linkable":168,"proposed":168,"self":168},{"name":172,"methodId":5,"linkable":168,"proposed":168,"self":168},{"name":174,"methodId":5,"linkable":168,"proposed":168,"self":168},[311,312,314,316,318,320,322,324,326,327,329,330,332,333,335,336,337,338,340,341,343,344,346,348,349,351,353,354],[177,177,177,247,179,177,179,179,177],[181,181,177,313,179,177,179,179,177],0.077,[184,181,177,315,179,177,179,179,177],0.009,[187,181,177,317,179,177,179,179,177],0.008,[177,177,181,319,179,177,179,179,177],0.026,[181,181,181,321,179,177,179,179,177],0.055,[184,181,181,323,179,177,179,179,177],0.018,[187,181,181,325,179,177,179,179,177],0.012,[177,177,184,185,179,177,179,179,177],[181,181,184,328,179,177,179,179,177],0.076,[184,181,184,317,179,177,179,179,177],[187,181,184,331,179,177,179,179,177],0.011,[177,177,187,237,179,177,179,179,177],[181,181,187,334,179,177,179,179,177],0.071,[184,181,187,315,179,177,179,179,177],[187,181,187,317,179,177,179,179,177],[177,177,190,237,179,177,179,179,177],[181,181,190,339,179,177,179,179,177],0.066,[184,181,190,264,179,177,179,179,177],[187,181,190,342,179,177,179,179,177],0.01,[177,177,193,252,179,177,179,179,177],[181,181,193,345,179,177,179,179,177],0.063,[184,181,193,347,179,177,179,179,177],0.006,[187,181,193,347,179,177,179,179,177],[177,184,196,350,179,177,179,179,177],0.039,[181,187,196,352,179,177,179,179,177],0.068,[184,187,196,331,179,177,179,179,177],[187,187,196,315,179,177,179,179,177],[],[282],[],[],[360],"TUM-VI room sequences (ground truth over the whole trajectory), RMS ATE (m) of ORB-SLAM3 in four sensor configurations, median of 3 executions; monocular aligned with 7 DoF, the others with 6 DoF",{"slug":362,"group":363,"sourceId":364,"sourceLabel":365,"table":123,"selfRows":366,"metrics":367,"seqs":377,"entrants":393,"cells":413,"outcomes":676,"locators":678,"hardware":679,"wordings":680,"notes":681},"livgs2025-table-ii","livgs2025:Table II","livgs2025","Xiao et al., 2025",18,[368,372,375],{"label":369,"unit":370,"statistic":129,"alignment":371},"t_rel (average translational RMSE drift)","%","not_reported",{"label":373,"unit":374,"statistic":129,"alignment":371},"r_rel (average rotational RMSE drift)","deg\u002F100 m",{"label":376,"unit":128,"statistic":129,"alignment":371},"t_abs (ATE RMSE)",[378,382,384,386,388,390],{"dataset":379,"sequence":380,"environment":381},"NTU4DRadLM","cp","outdoor, low-speed segment (cp about 230 m; garden and nyl segments at least 220 m each), Livox Horizon",{"dataset":379,"sequence":383,"environment":381},"garden1",{"dataset":379,"sequence":385,"environment":381},"garden2",{"dataset":379,"sequence":387,"environment":381},"nyl1",{"dataset":379,"sequence":389,"environment":381},"nyl2",{"dataset":379,"sequence":391,"environment":392},"loop2","outdoor, human-driven vehicle, high speed, 300 frames over about 250 m, Livox Horizon",[394,397,400,401,404,407,409,411],{"name":395,"methodId":396,"linkable":168,"proposed":79,"self":79},"NeRF-LOAM","nerfloam2023",{"name":398,"methodId":399,"linkable":79,"proposed":79,"self":79},"HDL-graph-SLAM","koide2019_hdlgraphslam",{"name":7,"methodId":5,"linkable":168,"proposed":79,"self":168},{"name":402,"methodId":403,"linkable":168,"proposed":79,"self":79},"SplaTAM","splatam2024",{"name":405,"methodId":406,"linkable":168,"proposed":79,"self":79},"MonoGS","monogs2024",{"name":408,"methodId":88,"linkable":79,"proposed":79,"self":79},"Gaussian-SLAM",{"name":410,"methodId":88,"linkable":79,"proposed":79,"self":79},"GS-ICP-SLAM",{"name":412,"methodId":364,"linkable":168,"proposed":168,"self":79},"Ours",[414,416,418,420,422,424,426,428,430,432,434,436,438,440,442,444,446,448,450,452,454,456,458,460,462,464,466,468,470,472,474,476,478,480,482,484,486,488,490,492,494,496,498,500,502,504,506,508,510,512,514,516,518,520,522,523,524,526,527,528,530,531,532,534,535,536,538,539,540,542,543,544,546,548,550,552,554,556,558,560,562,564,566,568,570,571,573,575,577,579,581,583,585,587,588,589,590,591,592,593,594,595,596,597,598,599,601,603,605,607,609,611,612,614,616,618,620,622,624,626,628,630,632,634,636,638,640,642,644,646,648,650,652,654,656,658,660,662,664,666,668,670,672,674],[177,177,177,415,179,177,179,179,177],2.943,[177,181,177,417,179,177,179,179,177],9.644,[177,184,177,419,179,177,179,179,177],5.39,[177,177,181,421,179,177,179,179,177],1.182,[177,181,181,423,179,177,179,179,177],0.559,[177,184,181,425,179,177,179,179,177],0.54,[177,177,184,427,179,177,179,179,177],1.213,[177,181,184,429,179,177,179,179,177],0.707,[177,184,184,431,179,177,179,179,177],1.076,[177,177,187,433,179,177,179,179,177],1.371,[177,181,187,435,179,177,179,179,177],1.14,[177,184,187,437,179,177,179,179,177],3.504,[177,177,190,439,179,177,179,179,177],1.343,[177,181,190,441,179,177,179,179,177],1.73,[177,184,190,443,179,177,179,179,177],17.46,[177,177,193,445,179,177,179,179,177],1.442,[177,181,193,447,179,177,179,179,177],2.205,[177,184,193,449,179,177,179,179,177],1.785,[181,177,177,451,179,177,179,179,177],1.264,[181,181,177,453,179,177,179,179,177],1.553,[181,184,177,455,179,177,179,179,177],1.079,[181,177,181,457,179,177,179,179,177],1.874,[181,181,181,459,179,177,179,179,177],1.603,[181,184,181,461,179,177,179,179,177],1.478,[181,177,184,463,179,177,179,179,177],1.186,[181,181,184,465,179,177,179,179,177],0.88,[181,184,184,467,179,177,179,179,177],3.154,[181,177,187,469,179,177,179,179,177],1.737,[181,181,187,471,179,177,179,179,177],1.271,[181,184,187,473,179,177,179,179,177],2.266,[181,177,190,475,179,177,179,179,177],1.514,[181,181,190,477,179,177,179,179,177],1.835,[181,184,190,479,179,177,179,179,177],17.638,[181,177,193,481,179,177,179,179,177],1.436,[181,181,193,483,179,177,179,179,177],2.802,[181,184,193,485,179,177,179,179,177],0.593,[184,177,177,487,179,177,179,179,177],1.356,[184,181,177,489,179,177,179,179,177],1.992,[184,184,177,491,179,177,179,179,177],2.865,[184,177,181,493,179,177,179,179,177],1.173,[184,181,181,495,179,177,179,179,177],0.626,[184,184,181,497,179,177,179,179,177],0.529,[184,177,184,499,179,177,179,179,177],1.212,[184,181,184,501,179,177,179,179,177],0.772,[184,184,184,503,179,177,179,179,177],1.001,[184,177,187,505,179,177,179,179,177],1.342,[184,181,187,507,179,177,179,179,177],1.172,[184,184,187,509,179,177,179,179,177],19.528,[184,177,190,511,179,177,179,179,177],1.333,[184,181,190,513,179,177,179,179,177],1.736,[184,184,190,515,179,177,179,179,177],23.283,[184,177,193,517,179,177,179,179,177],1.403,[184,181,193,519,179,177,179,179,177],2.256,[184,184,193,521,179,177,179,179,177],0.952,[187,177,177,88,177,177,179,179,177],[187,181,177,88,177,177,179,179,177],[187,184,177,525,179,177,179,179,177],2.336,[187,177,181,88,177,177,179,179,177],[187,181,181,88,177,177,179,179,177],[187,184,181,529,179,177,179,179,177],0.979,[187,177,184,88,177,177,179,179,177],[187,181,184,88,177,177,179,179,177],[187,184,184,533,179,177,179,179,177],1.221,[187,177,187,88,177,177,179,179,177],[187,181,187,88,177,177,179,179,177],[187,184,187,537,179,177,179,179,177],12.332,[187,177,190,88,177,177,179,179,177],[187,181,190,88,177,177,179,179,177],[187,184,190,541,179,177,179,179,177],17.442,[187,177,193,88,177,177,179,179,177],[187,181,193,88,177,177,179,179,177],[187,184,193,545,179,177,179,179,177],2.692,[190,177,177,547,179,177,179,179,177],4.171,[190,181,177,549,179,177,179,179,177],3.472,[190,184,177,551,179,177,179,179,177],3.44,[190,177,181,553,179,177,179,179,177],1.179,[190,181,181,555,179,177,179,179,177],0.754,[190,184,181,557,179,177,179,179,177],0.664,[190,177,184,559,179,177,179,179,177],1.163,[190,181,184,561,179,177,179,179,177],0.765,[190,184,184,563,179,177,179,179,177],0.708,[190,177,187,565,179,177,179,179,177],1.382,[190,181,187,567,179,177,179,179,177],1.175,[190,184,187,569,179,177,179,179,177],9.595,[190,177,190,433,179,177,179,179,177],[190,181,190,572,179,177,179,179,177],1.701,[190,184,190,574,179,177,179,179,177],28.553,[190,177,193,576,179,177,179,179,177],7.375,[190,181,193,578,179,177,179,179,177],5.708,[190,184,193,580,179,177,179,179,177],15.357,[193,177,177,582,179,177,179,179,177],1.249,[193,181,177,584,179,177,179,179,177],3.047,[193,184,177,586,179,177,179,179,177],1.04,[193,177,181,88,177,177,179,179,177],[193,181,181,88,177,177,179,179,177],[193,184,181,88,177,177,179,179,177],[193,177,184,88,177,177,179,179,177],[193,181,184,88,177,177,179,179,177],[193,184,184,88,177,177,179,179,177],[193,177,187,88,177,177,179,179,177],[193,181,187,88,177,177,179,179,177],[193,184,187,88,177,177,179,179,177],[193,177,190,88,177,177,179,179,177],[193,181,190,88,177,177,179,179,177],[193,184,190,88,177,177,179,179,177],[193,177,193,600,179,177,179,179,177],1.399,[193,181,193,602,179,177,179,179,177],2.384,[193,184,193,604,179,177,179,179,177],1.136,[196,177,177,606,179,177,179,179,177],5.471,[196,181,177,608,179,177,179,179,177],4.041,[196,184,177,610,179,177,179,179,177],6.33,[196,177,181,582,179,177,179,179,177],[196,181,181,613,179,177,179,179,177],0.764,[196,184,181,615,179,177,179,179,177],2.082,[196,177,184,617,179,177,179,179,177],1.824,[196,181,184,619,179,177,179,179,177],1.316,[196,184,184,621,179,177,179,179,177],5.507,[196,177,187,623,179,177,179,179,177],1.662,[196,181,187,625,179,177,179,179,177],1.771,[196,184,187,627,179,177,179,179,177],23.331,[196,177,190,629,179,177,179,179,177],2.101,[196,181,190,631,179,177,179,179,177],1.07,[196,184,190,633,179,177,179,179,177],23.915,[196,177,193,635,179,177,179,179,177],3.236,[196,181,193,637,179,177,179,179,177],2.644,[196,184,193,639,179,177,179,179,177],13.819,[199,177,177,641,179,177,179,179,177],0.234,[199,181,177,643,179,177,179,179,177],1.216,[199,184,177,645,179,177,179,179,177],0.464,[199,177,181,647,179,177,179,179,177],1.183,[199,181,181,649,179,177,179,179,177],0.716,[199,184,181,651,179,177,179,179,177],0.366,[199,177,184,653,179,177,179,179,177],1.236,[199,181,184,655,179,177,179,179,177],0.962,[199,184,184,657,179,177,179,179,177],0.679,[199,177,187,659,179,177,179,179,177],1.24,[199,181,187,661,179,177,179,179,177],1.307,[199,184,187,663,179,177,179,179,177],0.58,[199,177,190,665,179,177,179,179,177],1.106,[199,181,190,667,179,177,179,179,177],1.369,[199,184,190,669,179,177,179,179,177],0.771,[199,177,193,671,179,177,179,179,177],1.393,[199,181,193,673,179,177,179,179,177],2.239,[199,184,193,675,179,177,179,179,177],0.843,[677],"not reported ('-' in table)",[123],[],[],[682],"Tracking accuracy with rpg trajectory evaluation: t_rel = average translational RMSE drift (%), r_rel = average rotational RMSE drift (deg\u002F100 m), t_abs = ATE RMSE (m); reference trajectories from R3LIVE (not an independent measurement); alignment not stated; IMU not used by LiV-GS; '-' entries reported without explanation (text says indoor-oriented 3DGS SLAM methods degrade or fail on some outdoor sequences)",{"slug":684,"group":685,"sourceId":5,"sourceLabel":6,"table":686,"selfRows":687,"metrics":688,"seqs":692,"entrants":703,"cells":708,"outcomes":734,"locators":735,"hardware":736,"wordings":737,"notes":738},"orbslam3-2021-table-v","orbslam3_2021:Table V","Table V",16,[689,691],{"label":690,"unit":128,"statistic":129,"alignment":130},"Multi-session RMS ATE (m)",{"label":690,"unit":128,"statistic":129,"alignment":135},[693,695,697,700],{"dataset":95,"sequence":694,"environment":140},"MH01-03",{"dataset":95,"sequence":696,"environment":140},"MH01-05",{"dataset":95,"sequence":698,"environment":699},"V101-103","Vicon room 1, drone",{"dataset":95,"sequence":701,"environment":702},"V201-203","Vicon room 2, drone",[704,705,706,707],{"name":167,"methodId":5,"linkable":168,"proposed":168,"self":168},{"name":170,"methodId":5,"linkable":168,"proposed":168,"self":168},{"name":172,"methodId":5,"linkable":168,"proposed":168,"self":168},{"name":174,"methodId":5,"linkable":168,"proposed":168,"self":168},[709,711,713,714,716,717,719,720,722,723,725,726,728,729,731,733],[177,177,177,710,179,177,179,179,177],0.03,[177,177,181,712,179,177,179,179,177],0.058,[177,177,184,712,179,177,179,179,177],[177,177,187,715,179,177,179,179,177],0.284,[181,181,177,185,179,177,179,179,177],[181,181,181,718,179,177,179,179,177],0.04,[181,181,184,182,179,177,179,179,177],[181,181,187,721,179,177,179,179,177],0.163,[184,181,177,235,179,177,179,179,177],[184,181,181,724,179,177,179,179,177],0.065,[184,181,184,718,179,177,179,179,177],[184,181,187,727,179,177,179,179,177],0.048,[187,181,177,210,179,177,179,179,177],[187,181,181,730,179,177,179,179,177],0.047,[187,181,184,732,179,177,179,179,177],0.031,[187,181,187,237,179,177,179,179,177],[],[686],[],[],[739],"EuRoC multi-session: all sessions of one environment processed sequentially, single global alignment, RMS ATE (m); ORB-SLAM3 median of 5 executions against processed ground truth; CCM-SLAM and VINS values as reported by their authors; '-' cells and scale-error rows omitted",[741,749,757,763,768,774,780,786,792,799,806,812,817,822,827,833,839,845,850,854,858,863,867,872,880,888,895,899,903,907,911,916,920,924,929,933,939,944],{"group":742,"slug":743,"sourceLabel":744,"table":745,"selfRows":746,"datasets":747},"dpvslam2024:Table 2b","dpvslam2024-table-2b","Lipson et al., 2024","Table 2b",13,[748],"KITTI",{"group":750,"slug":751,"sourceLabel":752,"table":753,"selfRows":754,"datasets":755},"droidslam2021:Table 3","droidslam2021-table-3","Teed & Deng, 2021","Table 3",12,[756],"EuRoC MAV",{"group":758,"slug":759,"sourceLabel":760,"table":753,"selfRows":207,"datasets":761},"dpvo2023:Table 3","dpvo2023-table-3","Teed et al., 2023",[762],"TUM RGB-D",{"group":764,"slug":765,"sourceLabel":752,"table":766,"selfRows":207,"datasets":767},"droidslam2021:Table 4","droidslam2021-table-4","Table 4",[762],{"group":769,"slug":770,"sourceLabel":771,"table":123,"selfRows":207,"datasets":772},"maplab2_2023:Table II","maplab2-2023-table-ii","Cramariuc et al., 2023",[773],"HILTI 2021 SLAM Dataset",{"group":775,"slug":776,"sourceLabel":777,"table":753,"selfRows":204,"datasets":778},"goslam2023:Table 3","goslam2023-table-3","Zhang et al., 2023b",[779],"ScanNet",{"group":781,"slug":782,"sourceLabel":783,"table":282,"selfRows":204,"datasets":784},"viralfusion2022:Table IV","viralfusion2022-table-iv","Nguyen et al., 2022b",[785],"AirSim Building_99 (authors' simulation)",{"group":787,"slug":788,"sourceLabel":789,"table":766,"selfRows":204,"datasets":790},"zhao2024subtmrs:Table 4","zhao2024subtmrs-table-4","Zhao et al., 2024b",[791],"SubT-MRS (visual track)",{"group":793,"slug":794,"sourceLabel":795,"table":796,"selfRows":201,"datasets":797},"mins2025:Table 7","mins2025-table-7","Lee et al., 2025b","Table 7",[798],"UD Husky dataset",{"group":800,"slug":801,"sourceLabel":802,"table":803,"selfRows":201,"datasets":804},"photoslam2024:Table 1","photoslam2024-table-1","Huang et al., 2024c","Table 1",[805],"Replica",{"group":807,"slug":808,"sourceLabel":809,"table":803,"selfRows":199,"datasets":810},"yan2026tunnel:Table 1","yan2026tunnel-table-1","Yan et al., 2026a",[811],"Kimera-Multi Campus-Tunnel (KMCT)",{"group":813,"slug":814,"sourceLabel":802,"table":815,"selfRows":196,"datasets":816},"photoslam2024:Table 2","photoslam2024-table-2","Table 2",[762],{"group":818,"slug":819,"sourceLabel":783,"table":123,"selfRows":196,"datasets":820},"viralfusion2022:Table II","viralfusion2022-table-ii",[821],"EuRoC MAV (simulated UWB)",{"group":823,"slug":824,"sourceLabel":783,"table":825,"selfRows":196,"datasets":826},"viralfusion2022:Table III","viralfusion2022-table-iii","Table III",[821],{"group":828,"slug":829,"sourceLabel":789,"table":815,"selfRows":196,"datasets":830},"zhao2024subtmrs:Table 2","zhao2024subtmrs-table-2",[831,832],"SubT-MRS (ICCV 2023 SLAM Challenge, LiDAR track)","SubT-MRS (ICCV 2023 SLAM Challenge, visual track)",{"group":834,"slug":835,"sourceLabel":836,"table":837,"selfRows":193,"datasets":838},"deng2026_mcgs_slam:Table 11","deng2026-mcgs-slam-table-11","Deng & Gan, 2026","Table 11",[756],{"group":840,"slug":841,"sourceLabel":842,"table":843,"selfRows":193,"datasets":844},"monogs2024:Table 14","monogs2024-table-14","Matsuki et al., 2024","Table 14",[95],{"group":846,"slug":847,"sourceLabel":848,"table":815,"selfRows":190,"datasets":849},"gsicpslam2024:Table 2","gsicpslam2024-table-2","Ha et al., 2024",[762],{"group":851,"slug":852,"sourceLabel":6,"table":97,"selfRows":190,"datasets":853},"orbslam3_2021:Table VI","orbslam3-2021-table-vi",[95],{"group":855,"slug":856,"sourceLabel":802,"table":753,"selfRows":190,"datasets":857},"photoslam2024:Table 3","photoslam2024-table-3",[756],{"group":859,"slug":860,"sourceLabel":809,"table":815,"selfRows":190,"datasets":861},"yan2026tunnel:Table 2","yan2026tunnel-table-2",[862],"WHU-Helmet (WHUH)",{"group":864,"slug":865,"sourceLabel":836,"table":803,"selfRows":187,"datasets":866},"deng2026_mcgs_slam:Table 1","deng2026-mcgs-slam-table-1",[762],{"group":868,"slug":869,"sourceLabel":365,"table":282,"selfRows":187,"datasets":870},"livgs2025:Table IV","livgs2025-table-iv",[871],"R3LIVE dataset",{"group":873,"slug":874,"sourceLabel":875,"table":876,"selfRows":187,"datasets":877},"okvis2x2025:Text Sec.VI-H","okvis2x2025-text-sec-vi-h","Boche et al., 2025","Text Sec.VI-H",[756,878,879],"Hilti-Oxford","VBR",{"group":881,"slug":882,"sourceLabel":883,"table":803,"selfRows":187,"datasets":884},"splatam2024:Table 1","splatam2024-table-1","Keetha et al., 2024",[805,885,886,887],"ScanNet (original)","ScanNet++","TUM-RGBD",{"group":889,"slug":890,"sourceLabel":891,"table":892,"selfRows":184,"datasets":893},"mast3rslam2025:Fig. 5 table","mast3rslam2025-fig-5-table","Murai et al., 2025","Fig. 5 table",[894],"ETH3D-SLAM",{"group":896,"slug":897,"sourceLabel":891,"table":803,"selfRows":184,"datasets":898},"mast3rslam2025:Table 1","mast3rslam2025-table-1",[762],{"group":900,"slug":901,"sourceLabel":875,"table":123,"selfRows":184,"datasets":902},"okvis2x2025:Table II","okvis2x2025-table-ii",[756],{"group":904,"slug":905,"sourceLabel":875,"table":97,"selfRows":184,"datasets":906},"okvis2x2025:Table VI","okvis2x2025-table-vi",[879],{"group":908,"slug":909,"sourceLabel":836,"table":815,"selfRows":181,"datasets":910},"deng2026_mcgs_slam:Table 2","deng2026-mcgs-slam-table-2",[762],{"group":912,"slug":913,"sourceLabel":760,"table":803,"selfRows":181,"datasets":914},"dpvo2023:Table 1","dpvo2023-table-1",[915],"TartanAir",{"group":917,"slug":918,"sourceLabel":744,"table":803,"selfRows":181,"datasets":919},"dpvslam2024:Table 1","dpvslam2024-table-1",[762],{"group":921,"slug":922,"sourceLabel":744,"table":753,"selfRows":181,"datasets":923},"dpvslam2024:Table 3","dpvslam2024-table-3",[95],{"group":925,"slug":926,"sourceLabel":752,"table":927,"selfRows":181,"datasets":928},"droidslam2021:Table 5","droidslam2021-table-5","Table 5",[756],{"group":930,"slug":931,"sourceLabel":848,"table":803,"selfRows":181,"datasets":932},"gsicpslam2024:Table 1","gsicpslam2024-table-1",[805],{"group":934,"slug":935,"sourceLabel":795,"table":936,"selfRows":181,"datasets":937},"mins2025:Table 8 (Total column)","mins2025-table-8-total-column","Table 8 (Total column)",[938],"KAIST Urban",{"group":940,"slug":941,"sourceLabel":875,"table":282,"selfRows":181,"datasets":942},"okvis2x2025:Table IV","okvis2x2025-table-iv",[943],"Hilti-Oxford (Hilti 2022 challenge)",{"group":945,"slug":946,"sourceLabel":947,"table":815,"selfRows":181,"datasets":948},"vggtslam2025:Table 2","vggtslam2025-table-2","Maggio et al., 2025",[762],1790510656138]