[{"data":1,"prerenderedAt":903},["ShallowReactive",2],{"method-lsdslam2014":3},{"method":4,"reference":50,"equipment":71,"figures":85,"results":86},{"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":23,"limitations":26,"sensors":30,"platform":32,"estimator":34,"association":35,"timeModel":36,"deskew":37,"loopClosure":38,"globalOptimization":39,"mapRepresentation":40,"prior":41,"outputGeometry":42,"compute":43,"codeUrl":44,"codeLicense":45,"relatedVersions":46},"lsdslam2014","Engel et al., 2014","LSD-SLAM","LSD-SLAM: Large-Scale Direct Monocular SLAM",2014,"classic","C08","full_slam_with_global_correction","LSD-SLAM 為直接法（direct method）單眼 SLAM，不萃取特徵點，而是對影像梯度明顯的像素做光度誤差對齊，並以許多小基線立體比對濾波估計關鍵影格的半稠密（semi-dense）深度圖。新關鍵影格以 sim(3) 直接對齊連接鄰近關鍵影格，以明確偵測尺度漂移，並在位姿圖上做全域最佳化。地圖可輸出為半稠密點雲，但尺度仍非公制。","LSD-SLAM tracks a monocular camera by direct photometric alignment and builds a Sim(3) pose graph of keyframes carrying filtered semi-dense depth maps, explicitly modelling scale drift.","full_text_reviewed","peer_reviewed_published","background","論文未報告營建測試；以手持序列及 TUM RGB-D 評估。半稠密點雲僅來自影像梯度區域且尺度未定，用於工程幾何時需外部尺度與參考控制（推論）。",[20,21,22],"public_benchmark","controlled_experiment","simulation",[24,25],"Hand-held trajectories over 500 m with large scene-scale variation (conclusion)","Real-time on CPU (abstract)",[27,28,29],"Direct sim(3) image alignment is non-convex and needs accurate initialisation, which matters for loop-closure constraints; the authors report that ESM and a very coarse pyramid start enlarge the convergence radius so that it sufficed in practice even for large-scale loop closures (Sec. 3.5; Sec. 4.3)","ORB-SLAM authors note LSD-SLAM reduces map optimisation to a pose graph and discards sensor measurements (orbslam2015, Sec. IX-B)","Convergence of the random-depth initialisation is not thoroughly evaluated and is left to future work (Sec. 3.1)",[31],"monocular camera",[33],"handheld","weighted Gauss-Newton direct image alignment on se(3)\u002Fsim(3); keyframe pose-graph optimisation with Sim(3) edges (Sec. 2.2, 3.1)","direct photometric alignment on high-gradient (semi-dense) pixels; depth by filtering many small-baseline stereo comparisons (abstract; Sec. 3.1)","discrete poses (keyframes)","not_applicable","candidates from the ten closest keyframes plus an appearance-based candidate (OpenFABMAP, ref. [11]), accepted after a reciprocal sim(3) tracking consistency check (Sec. 3.5 Constraint Acquisition)","Sim(3) pose-graph optimisation of keyframes, run continuously in the background (Sec. 3.6 Map optimization; Fig. 3; conclusion)","Pose graph of keyframes; each keyframe stores the image, a semi-dense inverse depth map and its variance defined only near sufficiently large intensity gradients, scaled to mean inverse depth one; edges hold sim(3) transforms with covariance; the map can be exported as point clouds","No prior map. The method bootstraps from a first keyframe with random depth and large variance and needs sufficient translational motion in the first seconds; for the TUM RGB-D evaluation the very first sensor depth map was used to bootstrap and obtain the correct initial scale","semi-dense point cloud from keyframe depth maps and poses (conclusion); monocular, scale not metric","Real time on a CPU; the pipeline figure assumes 640x480 images at 30 Hz and map optimisation runs continuously in the background; no CPU model or timing numbers are reported (an odometry-only variant is cited as running on a smartphone, ref. [22])","https:\u002F\u002Fgithub.com\u002Ftum-vision\u002Flsd_slam","GPLv3 (LICENSE file)",[47],{"relation":48,"title":49,"doi_or_url":44},"code_release","lsd_slam",{"id":5,"kind":51,"shortName":7,"title":8,"authors":52,"year":9,"venue":56,"venueType":57,"publisher":58,"volumeIssuePages":59,"doi":60,"arxivId":61,"url":62,"firstPublicDate":63,"publicationStatus":16,"metadataStatus":64,"fulltextStatus":15,"era":10,"classicReason":65,"codeUrl":44,"cluster":11,"topics":66,"mdpi":67,"verification":68,"label":6,"fulltextRoute":69,"versionRead":70,"addedByCensus":67},"method",[53,54,55],"Jakob Engel","Thomas Schöps","Daniel Cremers","Computer Vision – ECCV 2014 (Lecture Notes in Computer Science)","conference","Springer","pp. 834-849","10.1007\u002F978-3-319-10605-2_54",null,"https:\u002F\u002Fjakobengel.github.io\u002Fpdf\u002Fengel14eccv.pdf","2014-09","metadata_verified","necessary technical node: first large-scale direct monocular SLAM with semi-dense keyframe depth maps and scale-drift-aware Sim(3) pose graph.",[11],false,"corrected","NTU institutional (curl)","Springer version of record (ECCV 2014, Part II, LNCS 8690, pp. 834-849), cross-checked against the authors' 16-page PDF (same content apart from layout)",[72,78],{"category":73,"model":74,"canonical":74,"role":75,"dataset":61,"specs":76,"locator":77},"camera","hand-held monocular camera (model not stated)","method input","pipeline figure assumes 640x480 at 30 Hz; used for the qualitative outdoor trajectories of about 500 m","Sec. 4, 4.1; Fig. 3",{"category":79,"model":80,"canonical":80,"role":81,"dataset":82,"specs":83,"locator":84},"rgbd","TUM RGB-D benchmark sensor (model not stated)","dataset sensor","TUM RGB-D","images used as monocular input; the first depth map used only for bootstrapping and initial scale","Sec. 4.2",[],{"totalRows":87,"groupCount":88,"groups":89,"others":879},87,8,[90,382,531,800],{"slug":91,"group":92,"sourceId":93,"sourceLabel":94,"table":95,"selfRows":96,"metrics":97,"seqs":106,"entrants":132,"cells":147,"outcomes":375,"locators":376,"hardware":377,"wordings":378,"notes":379},"cnnslam2017-table-1","cnnslam2017:Table 1","cnnslam2017","Tateno et al., 2017","Table 1",40,[98,103],{"label":99,"unit":100,"statistic":101,"alignment":102},"Abs. Trajectory Error [m]","m","RMSE","not_reported",{"label":104,"unit":105,"statistic":37,"alignment":37},"Perc. Correct Depth (error \u003C 10%)","%",[107,111,113,115,117,119,121,124,126,128],{"dataset":108,"sequence":109,"environment":110},"ICL-NUIM","office0","synthetic indoor (ICL-NUIM)",{"dataset":108,"sequence":112,"environment":110},"office1",{"dataset":108,"sequence":114,"environment":110},"office2",{"dataset":108,"sequence":116,"environment":110},"living0",{"dataset":108,"sequence":118,"environment":110},"living1",{"dataset":108,"sequence":120,"environment":110},"living2",{"dataset":82,"sequence":122,"environment":123},"fr3\u002Flong_office_household","real indoor office (Kinect)",{"dataset":82,"sequence":125,"environment":123},"fr3\u002Fnostructure_texture_near_withloop",{"dataset":82,"sequence":127,"environment":123},"fr3\u002Fstructure_texture_far",{"dataset":129,"sequence":130,"environment":131},"ICL-NUIM and TUM RGB-D","average of 9 sequences","indoor",[133,136,138,140,143,145],{"name":134,"methodId":61,"linkable":67,"proposed":135,"self":67},"CNN-SLAM (Our Method)",true,{"name":137,"methodId":5,"linkable":135,"proposed":67,"self":135},"LSD-BS [4] (LSD-SLAM bootstrapped with ground-truth depth)",{"name":139,"methodId":5,"linkable":135,"proposed":67,"self":135},"LSD [4] (LSD-SLAM)",{"name":141,"methodId":142,"linkable":135,"proposed":67,"self":67},"ORB [20] (ORB-SLAM)","orbslam2015",{"name":144,"methodId":61,"linkable":67,"proposed":67,"self":67},"Laina [16] (CNN depth fed to point-based fusion)",{"name":146,"methodId":61,"linkable":67,"proposed":67,"self":67},"Remode [23] (REMODE, poses from LSD-BS)",[148,152,155,158,161,164,166,168,170,172,174,177,179,181,183,185,187,189,191,193,195,197,199,201,203,205,207,209,211,213,215,217,219,221,223,225,227,229,231,233,235,237,239,241,242,244,246,248,250,252,254,256,258,260,262,264,266,268,270,272,274,276,278,280,282,284,286,289,291,293,295,297,299,301,303,305,307,309,312,314,316,318,320,322,324,326,327,329,331,333,335,337,339,341,343,345,347,348,350,352,355,357,359,361,363,365,367,369,371,373],[149,149,149,150,151,149,151,151,149],0,0.266,-1,[153,149,149,154,151,149,151,151,149],1,0.587,[156,149,149,157,151,149,151,151,149],2,0.528,[159,149,149,160,151,149,151,151,149],3,0.43,[162,149,149,163,151,149,151,151,149],4,0.337,[149,153,149,165,151,149,151,151,153],19.41,[153,153,149,167,151,149,151,151,153],0.603,[156,153,149,169,151,149,151,151,153],0.335,[159,153,149,171,151,149,151,151,153],0.018,[162,153,149,173,151,149,151,151,153],17.194,[175,153,149,176,151,149,151,151,153],5,4.479,[149,149,153,178,151,149,151,151,149],0.157,[153,149,153,180,151,149,151,151,149],0.79,[156,149,153,182,151,149,151,151,149],0.768,[159,149,153,184,151,149,151,151,149],0.78,[162,149,153,186,151,149,151,151,149],0.218,[149,153,153,188,151,149,151,151,153],29.15,[153,153,153,190,151,149,151,151,153],4.759,[156,153,153,192,151,149,151,151,153],0.038,[159,153,153,194,151,149,151,151,153],0.023,[162,153,153,196,151,149,151,151,153],20.838,[175,153,153,198,151,149,151,151,153],3.132,[149,149,156,200,151,149,151,151,149],0.213,[153,149,156,202,151,149,151,151,149],0.172,[156,149,156,204,151,149,151,151,149],0.794,[159,149,156,206,151,149,151,151,149],0.86,[162,149,156,208,151,149,151,151,149],0.509,[149,153,156,210,151,149,151,151,153],37.226,[153,153,156,212,151,149,151,151,153],1.435,[156,153,156,214,151,149,151,151,153],0.078,[159,153,156,216,151,149,151,151,153],0.04,[162,153,156,218,151,149,151,151,153],30.639,[175,153,156,220,151,149,151,151,153],16.7081,[149,149,159,222,151,149,151,151,149],0.196,[153,149,159,224,151,149,151,151,149],0.894,[156,149,159,226,151,149,151,151,149],0.516,[159,149,159,228,151,149,151,151,149],0.493,[162,149,159,230,151,149,151,151,149],0.23,[149,153,159,232,151,149,151,151,153],12.84,[153,153,159,234,151,149,151,151,153],1.443,[156,153,159,236,151,149,151,151,153],0.36,[159,153,159,238,151,149,151,151,153],0.027,[162,153,159,240,151,149,151,151,153],15.008,[175,153,159,176,151,149,151,151,153],[149,149,162,243,151,149,151,151,149],0.059,[153,149,162,245,151,149,151,151,149],0.54,[156,149,162,247,151,149,151,151,149],0.48,[159,149,162,249,151,149,151,151,149],0.129,[162,149,162,251,151,149,151,151,149],0.06,[149,153,162,253,151,149,151,151,153],13.038,[153,153,162,255,151,149,151,151,153],3.03,[156,153,162,257,151,149,151,151,153],0.057,[159,153,162,259,151,149,151,151,153],0.021,[162,153,162,261,151,149,151,151,153],11.449,[175,153,162,263,151,149,151,151,153],2.427,[149,149,175,265,151,149,151,151,149],0.323,[153,149,175,267,151,149,151,151,149],0.211,[156,149,175,269,151,149,151,151,149],0.667,[159,149,175,271,151,149,151,151,149],0.663,[162,149,175,273,151,149,151,151,149],0.38,[149,153,175,275,151,149,151,151,153],26.56,[153,153,175,277,151,149,151,151,153],1.807,[156,153,175,279,151,149,151,151,153],0.167,[159,153,175,281,151,149,151,151,153],0.014,[162,153,175,283,151,149,151,151,153],33.01,[175,153,175,285,151,149,151,151,153],8.681,[149,149,287,288,151,149,151,151,149],6,0.542,[153,149,287,290,151,149,151,151,149],1.717,[156,149,287,292,151,149,151,151,149],1.826,[159,149,287,294,151,149,151,151,149],1.206,[162,149,287,296,151,149,151,151,149],0.809,[149,153,287,298,151,149,151,151,153],12.477,[153,153,287,300,151,149,151,151,153],3.797,[156,153,287,302,151,149,151,151,153],0.086,[159,153,287,304,151,149,151,151,153],0.031,[162,153,287,306,151,149,151,151,153],12.982,[175,153,287,308,151,149,151,151,153],9.548,[149,149,310,311,151,149,151,151,149],7,0.243,[153,149,310,313,151,149,151,151,149],0.106,[156,149,310,315,151,149,151,151,149],0.436,[159,149,310,317,151,149,151,151,149],0.495,[162,149,310,319,151,149,151,151,149],1.337,[149,153,310,321,151,149,151,151,153],24.077,[153,153,310,323,151,149,151,151,153],3.966,[156,153,310,325,151,149,151,151,153],0.882,[159,153,310,243,151,149,151,151,153],[162,153,310,328,151,149,151,151,153],15.412,[175,153,310,330,151,149,151,151,153],12.651,[149,149,88,332,151,149,151,151,149],0.214,[153,149,88,334,151,149,151,151,149],0.037,[156,149,88,336,151,149,151,151,149],0.937,[159,149,88,338,151,149,151,151,149],0.733,[162,149,88,340,151,149,151,151,149],0.724,[149,153,88,342,151,149,151,151,153],27.396,[153,153,88,344,151,149,151,151,153],6.449,[156,153,88,346,151,149,151,151,153],0.035,[159,153,88,238,151,149,151,151,153],[162,153,88,349,151,149,151,151,153],9.45,[175,153,88,351,151,149,151,151,153],6.739,[149,149,353,354,151,149,151,151,149],9,0.246,[153,149,353,356,151,149,151,151,149],0.562,[156,149,353,358,151,149,151,151,149],0.772,[159,149,353,360,151,149,151,151,149],0.643,[162,149,353,362,151,149,151,151,149],0.512,[149,153,353,364,151,149,151,151,153],22.464,[153,153,353,366,151,149,151,151,153],3.032,[156,153,353,368,151,149,151,151,153],0.226,[159,153,353,370,151,149,151,151,153],0.029,[162,153,353,372,151,149,151,151,153],18.452,[175,153,353,374,151,149,151,151,153],7.649,[],[95],[],[],[380,381],"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":383,"group":384,"sourceId":142,"sourceLabel":385,"table":386,"selfRows":387,"metrics":388,"seqs":393,"entrants":427,"cells":434,"outcomes":522,"locators":526,"hardware":527,"wordings":528,"notes":529},"orbslam2015-table-iii","orbslam2015:Table III","Mur-Artal et al., 2015","Table III",16,[389],{"label":390,"unit":391,"statistic":101,"alignment":392},"Absolute KeyFrame Trajectory RMSE","cm","Sim3",[394,397,399,401,403,405,407,409,411,413,415,417,419,421,423,425],{"dataset":82,"sequence":395,"environment":396},"fr1_xyz","indoor, hand-held",{"dataset":82,"sequence":398,"environment":396},"fr2_xyz",{"dataset":82,"sequence":400,"environment":396},"fr1_floor",{"dataset":82,"sequence":402,"environment":396},"fr1_desk",{"dataset":82,"sequence":404,"environment":396},"fr2_360_kidnap",{"dataset":82,"sequence":406,"environment":396},"fr2_desk",{"dataset":82,"sequence":408,"environment":396},"fr3_long_office",{"dataset":82,"sequence":410,"environment":396},"fr3_nstr_tex_far",{"dataset":82,"sequence":412,"environment":396},"fr3_nstr_tex_near",{"dataset":82,"sequence":414,"environment":396},"fr3_str_tex_far",{"dataset":82,"sequence":416,"environment":396},"fr3_str_tex_near",{"dataset":82,"sequence":418,"environment":396},"fr2_desk_person",{"dataset":82,"sequence":420,"environment":396},"fr3_sit_xyz",{"dataset":82,"sequence":422,"environment":396},"fr3_sit_halfsph",{"dataset":82,"sequence":424,"environment":396},"fr3_walk_xyz",{"dataset":82,"sequence":426,"environment":396},"fr3_walk_halfsph",[428,430,433],{"name":429,"methodId":142,"linkable":135,"proposed":135,"self":67},"ORB-SLAM",{"name":431,"methodId":432,"linkable":135,"proposed":67,"self":67},"PTAM","ptam2007",{"name":7,"methodId":5,"linkable":135,"proposed":67,"self":135},[435,437,439,440,442,444,446,448,449,451,453,454,456,458,460,461,463,464,466,468,469,471,472,473,475,477,479,481,483,485,487,490,492,493,496,497,499,501,503,505,508,509,511,514,515,517,520,521],[149,149,149,436,151,149,151,151,149],0.9,[153,149,149,438,151,149,151,151,149],1.15,[156,149,149,353,151,149,151,151,149],[149,149,153,441,151,149,151,151,149],0.3,[153,149,153,443,151,149,151,151,149],0.2,[156,149,153,445,151,149,151,151,149],2.15,[149,149,156,447,151,149,151,151,149],2.99,[153,149,156,61,149,149,151,151,149],[156,149,156,450,151,149,151,151,149],38.07,[149,149,159,452,151,149,151,151,149],1.69,[153,149,159,61,149,149,151,151,149],[156,149,159,455,151,149,151,151,149],10.65,[149,149,162,457,151,149,151,151,149],3.81,[153,149,162,459,151,149,151,151,149],2.63,[156,149,162,61,149,149,151,151,149],[149,149,175,462,151,149,151,151,149],0.88,[153,149,175,61,149,149,151,151,149],[156,149,175,465,151,149,151,151,149],4.57,[149,149,287,467,151,149,151,151,149],3.45,[153,149,287,61,149,149,151,151,149],[156,149,287,470,151,149,151,151,149],38.53,[149,149,310,61,153,149,151,151,149],[153,149,310,61,156,149,151,151,149],[156,149,310,474,151,149,151,151,149],18.31,[149,149,88,476,151,149,151,151,149],1.39,[153,149,88,478,151,149,151,151,149],2.74,[156,149,88,480,151,149,151,151,149],7.54,[149,149,353,482,151,149,151,151,149],0.77,[153,149,353,484,151,149,151,151,149],0.93,[156,149,353,486,151,149,151,151,149],7.95,[149,149,488,489,151,149,151,151,149],10,1.58,[153,149,488,491,151,149,151,151,149],1.04,[156,149,488,61,149,149,151,151,149],[149,149,494,495,151,149,151,151,149],11,0.63,[153,149,494,61,149,149,151,151,149],[156,149,494,498,151,149,151,151,149],31.73,[149,149,500,180,151,149,151,151,149],12,[153,149,500,502,151,149,151,151,149],0.83,[156,149,500,504,151,149,151,151,149],7.73,[149,149,506,507,151,149,151,151,149],13,1.34,[153,149,506,61,149,149,151,151,149],[156,149,506,510,151,149,151,151,149],5.87,[149,149,512,513,151,149,151,151,149],14,1.24,[153,149,512,61,149,149,151,151,149],[156,149,512,516,151,149,151,151,149],12.44,[149,149,518,519,151,149,151,151,149],15,1.74,[153,149,518,61,149,149,151,151,149],[156,149,518,61,149,149,151,151,149],[523,524,525],"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)",[386],[],[],[530],"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",{"slug":532,"group":533,"sourceId":534,"sourceLabel":535,"table":536,"selfRows":494,"metrics":537,"seqs":540,"entrants":566,"cells":594,"outcomes":793,"locators":795,"hardware":796,"wordings":797,"notes":798},"svo2017-table-i","svo2017:Table I","svo2017","Forster et al., 2017b","Table I",[538],{"label":539,"unit":100,"statistic":101,"alignment":392},"absolute translation error (RMSE)",[541,545,547,549,551,553,556,558,560,562,564],{"dataset":542,"sequence":543,"environment":544},"EuRoC","Machine Hall 01","indoor machine hall, micro aerial vehicle",{"dataset":542,"sequence":546,"environment":544},"Machine Hall 02",{"dataset":542,"sequence":548,"environment":544},"Machine Hall 03",{"dataset":542,"sequence":550,"environment":544},"Machine Hall 04",{"dataset":542,"sequence":552,"environment":544},"Machine Hall 05",{"dataset":542,"sequence":554,"environment":555},"Vicon Room 1 01","indoor Vicon room, micro aerial vehicle",{"dataset":542,"sequence":557,"environment":555},"Vicon Room 1 02",{"dataset":542,"sequence":559,"environment":555},"Vicon Room 1 03",{"dataset":542,"sequence":561,"environment":555},"Vicon Room 2 01",{"dataset":542,"sequence":563,"environment":555},"Vicon Room 2 02",{"dataset":542,"sequence":565,"environment":555},"Vicon Room 2 03",[567,569,571,573,575,577,579,581,583,585,587,590,592],{"name":568,"methodId":534,"linkable":135,"proposed":135,"self":67},"SVO (stereo)",{"name":570,"methodId":534,"linkable":135,"proposed":135,"self":67},"SVO (stereo, edgelets)",{"name":572,"methodId":534,"linkable":135,"proposed":135,"self":67},"SVO (stereo, edgelets + prior)",{"name":574,"methodId":534,"linkable":135,"proposed":135,"self":67},"SVO (stereo, bundle adjustment)",{"name":576,"methodId":534,"linkable":135,"proposed":135,"self":67},"SVO (monocular)",{"name":578,"methodId":534,"linkable":135,"proposed":135,"self":67},"SVO (monocular, edgelets)",{"name":580,"methodId":534,"linkable":135,"proposed":135,"self":67},"SVO (monocular, edgelets + prior)",{"name":582,"methodId":534,"linkable":135,"proposed":135,"self":67},"SVO (monocular, bundle adjustment)",{"name":584,"methodId":142,"linkable":135,"proposed":67,"self":67},"ORB-SLAM (monocular, no loop-closure)",{"name":586,"methodId":142,"linkable":135,"proposed":67,"self":67},"ORB-SLAM (monocular, no loop, real-time)",{"name":588,"methodId":589,"linkable":135,"proposed":67,"self":67},"DSO (monocular)","dso2018",{"name":591,"methodId":589,"linkable":135,"proposed":67,"self":67},"DSO (monocular, real-time)",{"name":593,"methodId":5,"linkable":135,"proposed":67,"self":135},"LSD-SLAM (monocular, no loop-closure)",[595,597,598,599,600,602,603,605,606,608,610,612,613,615,616,618,619,620,622,623,625,626,628,630,631,632,634,636,637,638,639,640,642,644,645,646,648,649,651,653,655,657,658,659,661,662,663,665,667,669,671,673,675,676,677,678,679,681,683,684,685,687,689,691,693,695,696,697,698,699,700,701,702,703,705,707,708,710,711,713,714,715,716,717,719,721,722,723,725,726,727,729,730,731,732,733,734,735,736,737,738,739,740,742,743,744,745,746,747,748,749,750,751,752,754,755,756,757,759,761,762,763,764,765,766,767,768,770,772,774,775,776,777,778,779,780,781,783,784,786,788,790,792],[149,149,149,596,151,149,151,151,149],0.08,[153,149,149,596,151,149,151,151,149],[156,149,149,216,151,149,151,151,149],[159,149,149,216,151,149,151,151,149],[162,149,149,601,151,149,151,151,149],0.17,[175,149,149,601,151,149,151,151,149],[287,149,149,604,151,149,151,151,149],0.1,[310,149,149,251,151,149,151,151,149],[88,149,149,607,151,149,151,151,149],0.02,[353,149,149,609,151,149,151,151,149],0.61,[488,149,149,611,151,149,151,151,149],0.05,[494,149,149,611,151,149,151,151,149],[500,149,149,614,151,149,151,151,149],0.18,[149,149,153,596,151,149,151,151,149],[153,149,153,617,151,149,151,151,149],0.07,[156,149,153,617,151,149,151,151,149],[159,149,153,611,151,149,151,151,149],[162,149,153,621,151,149,151,151,149],0.27,[175,149,153,621,151,149,151,151,149],[287,149,153,624,151,149,151,151,149],0.12,[310,149,153,617,151,149,151,151,149],[88,149,153,627,151,149,151,151,149],0.03,[353,149,153,629,151,149,151,151,149],0.72,[488,149,153,611,151,149,151,151,149],[494,149,153,611,151,149,151,151,149],[500,149,153,633,151,149,151,151,149],0.56,[149,149,156,635,151,149,151,151,149],0.29,[153,149,156,621,151,149,151,151,149],[156,149,156,621,151,149,151,151,149],[159,149,156,251,151,149,151,151,149],[162,149,156,160,151,149,151,151,149],[175,149,156,641,151,149,151,151,149],0.42,[287,149,156,643,151,149,151,151,149],0.41,[310,149,156,61,149,149,151,151,149],[88,149,156,627,151,149,151,151,149],[353,149,156,647,151,149,151,151,149],1.7,[488,149,156,614,151,149,151,151,149],[494,149,156,650,151,149,151,151,149],0.26,[500,149,156,652,151,149,151,151,149],2.69,[149,149,159,654,151,149,151,151,149],2.67,[153,149,159,656,151,149,151,151,149],2.42,[156,149,159,601,151,149,151,151,149],[159,149,159,61,149,149,151,151,149],[162,149,159,660,151,149,151,151,149],1.36,[175,149,159,153,151,149,151,151,149],[287,149,159,160,151,149,151,151,149],[310,149,159,664,151,149,151,151,149],0.4,[88,149,159,666,151,149,151,151,149],0.22,[353,149,159,668,151,149,151,151,149],6.32,[488,149,159,670,151,149,151,151,149],2.5,[494,149,159,672,151,149,151,151,149],0.24,[500,149,159,674,151,149,151,151,149],2.13,[149,149,162,160,151,149,151,151,149],[153,149,162,245,151,149,151,151,149],[156,149,162,624,151,149,151,151,149],[159,149,162,624,151,149,151,151,149],[162,149,162,680,151,149,151,151,149],0.51,[175,149,162,682,151,149,151,151,149],0.6,[287,149,162,441,151,149,151,151,149],[310,149,162,61,149,149,151,151,149],[88,149,162,686,151,149,151,151,149],0.71,[353,149,162,688,151,149,151,151,149],5.66,[488,149,162,690,151,149,151,151,149],0.11,[494,149,162,692,151,149,151,151,149],0.15,[500,149,162,694,151,149,151,151,149],0.85,[149,149,175,611,151,149,151,151,149],[153,149,175,216,151,149,151,151,149],[156,149,175,216,151,149,151,151,149],[159,149,175,611,151,149,151,151,149],[162,149,175,443,151,149,151,151,149],[175,149,175,666,151,149,151,151,149],[287,149,175,617,151,149,151,151,149],[310,149,175,611,151,149,151,151,149],[88,149,175,704,151,149,151,151,149],0.16,[353,149,175,706,151,149,151,151,149],1.35,[488,149,175,624,151,149,151,151,149],[494,149,175,709,151,149,151,151,149],0.47,[500,149,175,513,151,149,151,151,149],[149,149,287,712,151,149,151,151,149],0.09,[153,149,287,596,151,149,151,151,149],[156,149,287,216,151,149,151,151,149],[159,149,287,611,151,149,151,151,149],[162,149,287,709,151,149,151,151,149],[175,149,287,718,151,149,151,151,149],0.35,[287,149,287,720,151,149,151,151,149],0.21,[310,149,287,61,149,149,151,151,149],[88,149,287,614,151,149,151,151,149],[353,149,287,724,151,149,151,151,149],0.58,[488,149,287,690,151,149,151,151,149],[494,149,287,604,151,149,151,151,149],[500,149,287,728,151,149,151,151,149],1.11,[149,149,310,236,151,149,151,151,149],[153,149,310,236,151,149,151,151,149],[156,149,310,617,151,149,151,151,149],[159,149,310,61,149,149,151,151,149],[162,149,310,61,149,149,151,151,149],[175,149,310,61,149,149,151,151,149],[287,149,310,61,149,149,151,151,149],[310,149,310,61,149,149,151,151,149],[88,149,310,184,151,149,151,151,149],[353,149,310,495,151,149,151,151,149],[488,149,310,484,151,149,151,151,149],[494,149,310,741,151,149,151,151,149],0.66,[500,149,310,61,149,149,151,151,149],[149,149,88,712,151,149,151,151,149],[153,149,88,617,151,149,151,151,149],[156,149,88,611,151,149,151,151,149],[159,149,88,611,151,149,151,151,149],[162,149,88,441,151,149,151,151,149],[175,149,88,650,151,149,151,151,149],[287,149,88,690,151,149,151,151,149],[310,149,88,61,149,149,151,151,149],[88,149,88,607,151,149,151,151,149],[353,149,88,753,151,149,151,151,149],0.53,[488,149,88,216,151,149,151,151,149],[494,149,88,611,151,149,151,151,149],[500,149,88,61,149,149,151,151,149],[149,149,353,758,151,149,151,151,149],0.52,[153,149,353,760,151,149,151,151,149],0.14,[156,149,353,712,151,149,151,151,149],[159,149,353,61,149,149,151,151,149],[162,149,353,709,151,149,151,151,149],[175,149,353,664,151,149,151,151,149],[287,149,353,690,151,149,151,151,149],[310,149,353,61,149,149,151,151,149],[88,149,353,720,151,149,151,151,149],[353,149,353,769,151,149,151,151,149],0.68,[488,149,353,771,151,149,151,151,149],0.13,[494,149,353,773,151,149,151,151,149],0.19,[500,149,353,61,149,149,151,151,149],[149,149,488,61,149,149,151,151,149],[153,149,488,61,149,149,151,151,149],[156,149,488,180,151,149,151,151,149],[159,149,488,61,149,149,151,151,149],[162,149,488,61,149,149,151,151,149],[175,149,488,61,149,149,151,151,149],[287,149,488,782,151,149,151,151,149],1.08,[310,149,488,61,149,149,151,151,149],[88,149,488,785,151,149,151,151,149],1.25,[353,149,488,787,151,149,151,151,149],1.06,[488,149,488,789,151,149,151,151,149],1.16,[494,149,488,791,151,149,151,151,149],1.19,[500,149,488,61,149,149,151,151,149],[794],"failed",[536],[],[],[799],"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":801,"group":802,"sourceId":803,"sourceLabel":804,"table":805,"selfRows":88,"metrics":806,"seqs":809,"entrants":823,"cells":830,"outcomes":873,"locators":874,"hardware":875,"wordings":876,"notes":877},"deepfactors2020-table-ii","deepfactors2020:Table II","deepfactors2020","Czarnowski et al., 2020","Table II",[807],{"label":808,"unit":105,"statistic":37,"alignment":102},"Perc. Correct Depth [%]",[810,812,813,814,815,817,819,821],{"dataset":108,"sequence":109,"environment":811},"indoor (synthetic ICL-NUIM, real TUM)",{"dataset":108,"sequence":112,"environment":811},{"dataset":108,"sequence":116,"environment":811},{"dataset":108,"sequence":118,"environment":811},{"dataset":82,"sequence":816,"environment":811},"fr3_long_office_household",{"dataset":82,"sequence":818,"environment":811},"fr3_nostructure_texture_near_withloop",{"dataset":82,"sequence":820,"environment":811},"fr3_structure_texture_far",{"dataset":129,"sequence":822,"environment":811},"average of 7 sequences",[824,826,828],{"name":825,"methodId":61,"linkable":67,"proposed":67,"self":67},"CNN-SLAM [ 18 ]",{"name":827,"methodId":5,"linkable":135,"proposed":67,"self":135},"LSD-BS [ 19 ]",{"name":829,"methodId":61,"linkable":67,"proposed":67,"self":67},"Laina [ 37 ]",[831,832,833,835,836,838,840,841,843,845,847,848,850,852,854,856,858,860,862,864,866,867,869,871],[149,149,149,165,151,149,151,151,149],[153,149,149,682,151,149,151,151,149],[156,149,149,834,151,149,151,151,149],17.19,[149,149,153,188,151,149,151,151,149],[153,149,153,837,151,149,151,151,149],4.76,[156,149,153,839,151,149,151,151,149],20.84,[149,149,156,232,151,149,151,151,149],[153,149,156,842,151,149,151,151,149],1.44,[156,149,156,844,151,149,151,151,149],15.01,[149,149,159,846,151,149,151,151,149],13.04,[153,149,159,255,151,149,151,151,149],[156,149,159,849,151,149,151,151,149],11.45,[149,149,162,851,151,149,151,151,149],12.48,[153,149,162,853,151,149,151,151,149],3.8,[156,149,162,855,151,149,151,151,149],12.98,[149,149,175,857,151,149,151,151,149],24.08,[153,149,175,859,151,149,151,151,149],3.97,[156,149,175,861,151,149,151,151,149],15.41,[149,149,287,863,151,149,151,151,149],27.4,[153,149,287,865,151,149,151,151,149],6.45,[156,149,287,349,151,149,151,151,149],[149,149,310,868,151,149,151,151,149],19.77,[153,149,310,870,151,149,151,151,149],3.44,[156,149,310,872,151,149,151,151,149],14.62,[],[805],[],[],[878],"Percentage of key-frame pixels with depth within 10% of ground truth; DeepFactors trajectory and depth scaled by the optimal scale from the TUM scripts; other values taken from the CNN-SLAM paper",[880,886,892,896],{"group":881,"slug":882,"sourceLabel":883,"table":884,"selfRows":162,"datasets":885},"bundlefusion2017:Table 4","bundlefusion2017-table-4","Dai et al., 2017a","Table 4",[82],{"group":887,"slug":888,"sourceLabel":6,"table":889,"selfRows":162,"datasets":890},"lsdslam2014:Fig. 9","lsdslam2014-fig-9","Fig. 9",[82,891],"synthetic sequences (Handa et al. 2012)",{"group":893,"slug":894,"sourceLabel":535,"table":805,"selfRows":159,"datasets":895},"svo2017:Table II","svo2017-table-ii",[542],{"group":897,"slug":898,"sourceLabel":899,"table":900,"selfRows":153,"datasets":901},"ghadimzadeh2025slamnde:Table 2","ghadimzadeh2025slamnde-table-2","Ghadimzadeh Alamdari et al., 2025","Table 2",[902],"Luleå SubT tunnel dataset (Koval et al. 2022)",1790510658735]