[{"data":1,"prerenderedAt":922},["ShallowReactive",2],{"method-dso2018":3},{"method":4,"reference":63,"equipment":83,"figures":108,"results":109},{"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":22,"limitations":29,"sensors":36,"platform":38,"estimator":43,"association":44,"timeModel":45,"deskew":46,"loopClosure":47,"globalOptimization":48,"mapRepresentation":49,"prior":50,"outputGeometry":51,"compute":52,"codeUrl":53,"codeLicense":54,"relatedVersions":55},"dso2018","Engel et al., 2018","DSO","Direct Sparse Odometry",2018,"classic","C08","odometry_with_local_mapping","DSO 是直接稀疏法的單眼視覺里程計（visual odometry），直接最小化光度誤差，並在滑動視窗內聯合最佳化相機位姿、相機內參、仿射亮度參數與逆深度，舊狀態以邊際化（marginalization）移除。它不使用平滑先驗，而是在影像中均勻取樣具梯度的像素，包括白牆上的弱梯度與邊緣，並整合曝光、暗角與非線性響應的光度校正。DSO 不含迴圈閉合，屬里程計而非完整 SLAM。","DSO is a direct sparse monocular odometry that jointly optimises poses, intrinsics, affine brightness and inverse depths in a marginalised sliding window, sampling gradient pixels evenly and using full photometric calibration; it has no loop closure.","full_text_reviewed","peer_reviewed_published","background","論文未報告營建測試；評估資料為 TUM monoVO、EuRoC 與 ICL-NUIM。作者指出可利用白牆弱梯度，但對捲簾快門與內參誤差敏感，現場使用消費型相機時須注意（推論）。",[20,21],"public_benchmark","simulation",[23,24,25,26,27,28],"Can use pixels on edges and smooth intensity variations on mostly white walls (abstract)","Photometric calibration improves performance versus brightness constancy (Sec. 4.2, Fig. 15; Sec. 5)","With high settings produces semi-dense models similar in density to LSD-SLAM (Sec. 1.2)","Restricting candidates to FAST corners clearly reduces accuracy and robustness (Sec. 4.2, Fig. 17)","Slightly more robust than ORB-SLAM to strong photometric noise (simulated anisotropic blur) (Sec. 4.3, Fig. 21)","Outperforms ORB-SLAM in accuracy and robustness on TUM monoVO and ICL-NUIM (Sec. 4.1)",[30,31,32,33,34,35],"Indirect (geometric-error) approaches are more robust to geometric noise such as poor intrinsic calibration or rolling shutter (Sec. 4.3; Sec. 5)","Using more points makes models denser but does not increase tracking accuracy (Sec. 4.2; Sec. 5)","No loop closure or relocalization; points and frames leaving the view are permanently marginalised (Sec. 4.1)","On EuRoC MAV ORB-SLAM is more accurate (but less robust), attributed to missing photometric calibration and many small loops (Sec. 4.1)","Fewer than about 4 keyframes per second reduces robustness and more than 15 reduces accuracy (Sec. 4.2)","Higher non-convexity of the photometric model likely restricts it to video processing (Sec. 5)",[37],"monocular camera",[39,40,41,42],"UAV (EuRoC MAV quadrocopter sequences, left and right images used separately)","TUM monoVO sequences, 50 photometrically calibrated indoor and outdoor videos (carrying mode not stated in this paper)","synthetic ray-traced ICL-NUIM sequences","Fig. 1 video recorded while cycling around a building","sliding-window Gauss-Newton (up to 6 iterations per new keyframe, no Levenberg-Marquardt damping) jointly over poses, affine brightness parameters, inverse depths and camera intrinsics, with First Estimate Jacobians and Schur-complement marginalisation; window Nf = 7 keyframes and Np = 2000 active points; keyframes marginalised by a distance score and residuals that would break Hessian sparsity are dropped (about half of all residuals)","direct photometric error of an 8-pixel residual pattern with Huber norm and gradient-dependent weighting, on points sampled with a region-adaptive gradient threshold (32x32 blocks, three passes with lower thresholds); inverse depth in a host frame; candidates tracked by discrete epipolar search before activation; new frames tracked by two-frame direct alignment to the newest keyframe's projected semi-dense depth map with a constant motion model, with up to 27 small-rotation retries on failure","discrete poses (keyframes)","not_applicable (rolling shutter not modelled; simulated as low-frequency geometric noise in Sec. 4.3, where DSO degrades much faster than ORB-SLAM and, according to the authors, optimisation likely fails entirely for noise amplitude above 1.5 (alleviable with a coarser pyramid level); tight rolling-shutter modelling cited as remedy)","none (visual odometry; explicit loop closure disabled for ORB-SLAM in comparisons for fairness, Sec. 4)","none","sparse set of points with inverse depth in active keyframes","photometric calibration (exposure time, vignetting, response function) (abstract)","point clouds accumulated from the odometry without loop closure, density set by the number of active points (Np = 500 to 10000 shown); monocular scale unobservable (scale is a null space of the energy) and evaluated with Sim(3) alignment and scale drift","CPU only; real time on a laptop; hard-enforced real-time evaluations on an Intel i7-4910MQ CPU; non-real-time evaluation in a sequentialised single-threaded mode about four times slower than real time on 20 dedicated workstations; reduced settings run at 5 times real time","https:\u002F\u002Fgithub.com\u002FJakobEngel\u002Fdso","GPLv3 (LICENSE file)",[56,60],{"relation":57,"title":58,"doi_or_url":59},"preprint","Direct Sparse Odometry (arXiv)","https:\u002F\u002Farxiv.org\u002Fabs\u002F1607.02565",{"relation":61,"title":62,"doi_or_url":53},"code_release","dso",{"id":5,"kind":64,"shortName":7,"title":8,"authors":65,"year":9,"venue":69,"venueType":70,"publisher":71,"volumeIssuePages":72,"doi":73,"arxivId":74,"url":59,"firstPublicDate":75,"publicationStatus":16,"metadataStatus":76,"fulltextStatus":15,"era":10,"classicReason":77,"codeUrl":53,"cluster":11,"topics":78,"mdpi":79,"verification":80,"label":6,"fulltextRoute":81,"versionRead":82,"addedByCensus":79},"method",[66,67,68],"Jakob Engel","Vladlen Koltun","Daniel Cremers","IEEE Transactions on Pattern Analysis and Machine Intelligence","journal","IEEE","40(3):611-625","10.1109\u002Ftpami.2017.2658577","1607.02565","2016-07-09","metadata_verified","reproducible baseline and principle reused: first public 2016-07-09 (arXiv), before the recent window; defines direct sparse windowed photometric BA with full photometric calibration.",[11],false,"confirmed","arXiv","arXiv 1607.02565v2 (2016-10-07; v2 comment: corrected a bug that made ORB-SLAM real-time results worse, added refs [12], [13], [19] and Fig. 11, extended conclusion); IEEE TPAMI 40(3) version of record not compared",[84,91,95,102],{"category":85,"model":86,"canonical":86,"role":87,"dataset":88,"specs":89,"locator":90},"compute","Intel i7-4910MQ CPU","compute for runtime",null,"hard-enforced real-time evaluation","Sec. 4.1",{"category":85,"model":92,"canonical":92,"role":87,"dataset":88,"specs":93,"locator":94},"20 dedicated workstations (model not reported)","non-real-time sequentialised evaluation runs","Sec. 4 Methodology",{"category":96,"model":97,"canonical":97,"role":98,"dataset":99,"specs":100,"locator":101},"stereo_camera","EuRoC MAV stereo camera (model not reported in this paper)","dataset sensor","EuRoC MAV","11 stereo-inertial sequences, 19 minutes; left and right videos used separately as monocular input; no photometric calibration or exposure times; shaky initialisation segments cropped","Sec. 4 datasets and Methodology",{"category":103,"model":104,"canonical":104,"role":98,"dataset":105,"specs":106,"locator":107},"camera","TUM monoVO camera (model not reported in this paper)","TUM monoVO","50 photometrically calibrated sequences (response, vignetting, exposure times), 105 minutes, about 190,000 frames; exposure varied from 0.018 to 10.5 ms in an indoor-outdoor sequence","Sec. 2.1.2, Fig. 3; Sec. 4 datasets; Fig. 11",[],{"totalRows":110,"groupCount":111,"groups":112,"others":848},104,17,[113,414,567,736],{"slug":114,"group":115,"sourceId":116,"sourceLabel":117,"table":118,"selfRows":119,"metrics":120,"seqs":126,"entrants":152,"cells":182,"outcomes":407,"locators":409,"hardware":410,"wordings":411,"notes":412},"svo2017-table-i","svo2017:Table I","svo2017","Forster et al., 2017b","Table I",22,[121],{"label":122,"unit":123,"statistic":124,"alignment":125},"absolute translation error (RMSE)","m","RMSE","Sim3",[127,131,133,135,137,139,142,144,146,148,150],{"dataset":128,"sequence":129,"environment":130},"EuRoC","Machine Hall 01","indoor machine hall, micro aerial vehicle",{"dataset":128,"sequence":132,"environment":130},"Machine Hall 02",{"dataset":128,"sequence":134,"environment":130},"Machine Hall 03",{"dataset":128,"sequence":136,"environment":130},"Machine Hall 04",{"dataset":128,"sequence":138,"environment":130},"Machine Hall 05",{"dataset":128,"sequence":140,"environment":141},"Vicon Room 1 01","indoor Vicon room, micro aerial vehicle",{"dataset":128,"sequence":143,"environment":141},"Vicon Room 1 02",{"dataset":128,"sequence":145,"environment":141},"Vicon Room 1 03",{"dataset":128,"sequence":147,"environment":141},"Vicon Room 2 01",{"dataset":128,"sequence":149,"environment":141},"Vicon Room 2 02",{"dataset":128,"sequence":151,"environment":141},"Vicon Room 2 03",[153,156,158,160,162,164,166,168,170,173,175,177,179],{"name":154,"methodId":116,"linkable":155,"proposed":155,"self":79},"SVO (stereo)",true,{"name":157,"methodId":116,"linkable":155,"proposed":155,"self":79},"SVO (stereo, edgelets)",{"name":159,"methodId":116,"linkable":155,"proposed":155,"self":79},"SVO (stereo, edgelets + prior)",{"name":161,"methodId":116,"linkable":155,"proposed":155,"self":79},"SVO (stereo, bundle adjustment)",{"name":163,"methodId":116,"linkable":155,"proposed":155,"self":79},"SVO (monocular)",{"name":165,"methodId":116,"linkable":155,"proposed":155,"self":79},"SVO (monocular, edgelets)",{"name":167,"methodId":116,"linkable":155,"proposed":155,"self":79},"SVO (monocular, edgelets + prior)",{"name":169,"methodId":116,"linkable":155,"proposed":155,"self":79},"SVO (monocular, bundle adjustment)",{"name":171,"methodId":172,"linkable":155,"proposed":79,"self":79},"ORB-SLAM (monocular, no loop-closure)","orbslam2015",{"name":174,"methodId":172,"linkable":155,"proposed":79,"self":79},"ORB-SLAM (monocular, no loop, real-time)",{"name":176,"methodId":5,"linkable":155,"proposed":79,"self":155},"DSO (monocular)",{"name":178,"methodId":5,"linkable":155,"proposed":79,"self":155},"DSO (monocular, real-time)",{"name":180,"methodId":181,"linkable":155,"proposed":79,"self":79},"LSD-SLAM (monocular, no loop-closure)","lsdslam2014",[183,187,189,192,194,197,199,202,205,208,211,214,216,219,220,222,223,224,226,227,229,230,232,234,235,236,238,240,241,242,243,245,247,249,250,251,253,254,256,258,260,262,263,264,266,267,268,270,272,274,276,278,280,281,283,284,285,287,289,291,292,294,296,298,300,302,303,304,305,306,308,309,310,311,313,315,316,318,320,322,323,324,325,326,328,330,331,332,334,335,336,338,340,341,342,343,344,345,346,347,349,351,353,355,356,357,358,359,360,361,362,363,364,365,367,368,369,370,372,374,375,376,377,378,379,380,381,383,385,387,388,389,390,392,393,394,395,397,398,400,402,404,406],[184,184,184,185,186,184,186,186,184],0,0.08,-1,[188,184,184,185,186,184,186,186,184],1,[190,184,184,191,186,184,186,186,184],2,0.04,[193,184,184,191,186,184,186,186,184],3,[195,184,184,196,186,184,186,186,184],4,0.17,[198,184,184,196,186,184,186,186,184],5,[200,184,184,201,186,184,186,186,184],6,0.1,[203,184,184,204,186,184,186,186,184],7,0.06,[206,184,184,207,186,184,186,186,184],8,0.02,[209,184,184,210,186,184,186,186,184],9,0.61,[212,184,184,213,186,184,186,186,184],10,0.05,[215,184,184,213,186,184,186,186,184],11,[217,184,184,218,186,184,186,186,184],12,0.18,[184,184,188,185,186,184,186,186,184],[188,184,188,221,186,184,186,186,184],0.07,[190,184,188,221,186,184,186,186,184],[193,184,188,213,186,184,186,186,184],[195,184,188,225,186,184,186,186,184],0.27,[198,184,188,225,186,184,186,186,184],[200,184,188,228,186,184,186,186,184],0.12,[203,184,188,221,186,184,186,186,184],[206,184,188,231,186,184,186,186,184],0.03,[209,184,188,233,186,184,186,186,184],0.72,[212,184,188,213,186,184,186,186,184],[215,184,188,213,186,184,186,186,184],[217,184,188,237,186,184,186,186,184],0.56,[184,184,190,239,186,184,186,186,184],0.29,[188,184,190,225,186,184,186,186,184],[190,184,190,225,186,184,186,186,184],[193,184,190,204,186,184,186,186,184],[195,184,190,244,186,184,186,186,184],0.43,[198,184,190,246,186,184,186,186,184],0.42,[200,184,190,248,186,184,186,186,184],0.41,[203,184,190,88,184,184,186,186,184],[206,184,190,231,186,184,186,186,184],[209,184,190,252,186,184,186,186,184],1.7,[212,184,190,218,186,184,186,186,184],[215,184,190,255,186,184,186,186,184],0.26,[217,184,190,257,186,184,186,186,184],2.69,[184,184,193,259,186,184,186,186,184],2.67,[188,184,193,261,186,184,186,186,184],2.42,[190,184,193,196,186,184,186,186,184],[193,184,193,88,184,184,186,186,184],[195,184,193,265,186,184,186,186,184],1.36,[198,184,193,188,186,184,186,186,184],[200,184,193,244,186,184,186,186,184],[203,184,193,269,186,184,186,186,184],0.4,[206,184,193,271,186,184,186,186,184],0.22,[209,184,193,273,186,184,186,186,184],6.32,[212,184,193,275,186,184,186,186,184],2.5,[215,184,193,277,186,184,186,186,184],0.24,[217,184,193,279,186,184,186,186,184],2.13,[184,184,195,244,186,184,186,186,184],[188,184,195,282,186,184,186,186,184],0.54,[190,184,195,228,186,184,186,186,184],[193,184,195,228,186,184,186,186,184],[195,184,195,286,186,184,186,186,184],0.51,[198,184,195,288,186,184,186,186,184],0.6,[200,184,195,290,186,184,186,186,184],0.3,[203,184,195,88,184,184,186,186,184],[206,184,195,293,186,184,186,186,184],0.71,[209,184,195,295,186,184,186,186,184],5.66,[212,184,195,297,186,184,186,186,184],0.11,[215,184,195,299,186,184,186,186,184],0.15,[217,184,195,301,186,184,186,186,184],0.85,[184,184,198,213,186,184,186,186,184],[188,184,198,191,186,184,186,186,184],[190,184,198,191,186,184,186,186,184],[193,184,198,213,186,184,186,186,184],[195,184,198,307,186,184,186,186,184],0.2,[198,184,198,271,186,184,186,186,184],[200,184,198,221,186,184,186,186,184],[203,184,198,213,186,184,186,186,184],[206,184,198,312,186,184,186,186,184],0.16,[209,184,198,314,186,184,186,186,184],1.35,[212,184,198,228,186,184,186,186,184],[215,184,198,317,186,184,186,186,184],0.47,[217,184,198,319,186,184,186,186,184],1.24,[184,184,200,321,186,184,186,186,184],0.09,[188,184,200,185,186,184,186,186,184],[190,184,200,191,186,184,186,186,184],[193,184,200,213,186,184,186,186,184],[195,184,200,317,186,184,186,186,184],[198,184,200,327,186,184,186,186,184],0.35,[200,184,200,329,186,184,186,186,184],0.21,[203,184,200,88,184,184,186,186,184],[206,184,200,218,186,184,186,186,184],[209,184,200,333,186,184,186,186,184],0.58,[212,184,200,297,186,184,186,186,184],[215,184,200,201,186,184,186,186,184],[217,184,200,337,186,184,186,186,184],1.11,[184,184,203,339,186,184,186,186,184],0.36,[188,184,203,339,186,184,186,186,184],[190,184,203,221,186,184,186,186,184],[193,184,203,88,184,184,186,186,184],[195,184,203,88,184,184,186,186,184],[198,184,203,88,184,184,186,186,184],[200,184,203,88,184,184,186,186,184],[203,184,203,88,184,184,186,186,184],[206,184,203,348,186,184,186,186,184],0.78,[209,184,203,350,186,184,186,186,184],0.63,[212,184,203,352,186,184,186,186,184],0.93,[215,184,203,354,186,184,186,186,184],0.66,[217,184,203,88,184,184,186,186,184],[184,184,206,321,186,184,186,186,184],[188,184,206,221,186,184,186,186,184],[190,184,206,213,186,184,186,186,184],[193,184,206,213,186,184,186,186,184],[195,184,206,290,186,184,186,186,184],[198,184,206,255,186,184,186,186,184],[200,184,206,297,186,184,186,186,184],[203,184,206,88,184,184,186,186,184],[206,184,206,207,186,184,186,186,184],[209,184,206,366,186,184,186,186,184],0.53,[212,184,206,191,186,184,186,186,184],[215,184,206,213,186,184,186,186,184],[217,184,206,88,184,184,186,186,184],[184,184,209,371,186,184,186,186,184],0.52,[188,184,209,373,186,184,186,186,184],0.14,[190,184,209,321,186,184,186,186,184],[193,184,209,88,184,184,186,186,184],[195,184,209,317,186,184,186,186,184],[198,184,209,269,186,184,186,186,184],[200,184,209,297,186,184,186,186,184],[203,184,209,88,184,184,186,186,184],[206,184,209,329,186,184,186,186,184],[209,184,209,382,186,184,186,186,184],0.68,[212,184,209,384,186,184,186,186,184],0.13,[215,184,209,386,186,184,186,186,184],0.19,[217,184,209,88,184,184,186,186,184],[184,184,212,88,184,184,186,186,184],[188,184,212,88,184,184,186,186,184],[190,184,212,391,186,184,186,186,184],0.79,[193,184,212,88,184,184,186,186,184],[195,184,212,88,184,184,186,186,184],[198,184,212,88,184,184,186,186,184],[200,184,212,396,186,184,186,186,184],1.08,[203,184,212,88,184,184,186,186,184],[206,184,212,399,186,184,186,186,184],1.25,[209,184,212,401,186,184,186,186,184],1.06,[212,184,212,403,186,184,186,186,184],1.16,[215,184,212,405,186,184,186,186,184],1.19,[217,184,212,88,184,184,186,186,184],[408],"failed",[118],[],[],[413],"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":415,"group":416,"sourceId":417,"sourceLabel":418,"table":419,"selfRows":420,"metrics":421,"seqs":425,"entrants":448,"cells":463,"outcomes":561,"locators":562,"hardware":563,"wordings":564,"notes":565},"dpvo2023-table-3","dpvo2023:Table 3","dpvo2023","Teed et al., 2023","Table 3",20,[422],{"label":423,"unit":424,"statistic":424,"alignment":125},"ATE","not_reported",[426,430,432,434,436,438,440,442,444,446],{"dataset":427,"sequence":428,"environment":429},"TUM RGB-D","fr1\u002F360","indoor, erratic motion and motion blur",{"dataset":427,"sequence":431,"environment":429},"fr1\u002Fdesk",{"dataset":427,"sequence":433,"environment":429},"fr1\u002Fdesk2",{"dataset":427,"sequence":435,"environment":429},"fr1\u002Ffloor",{"dataset":427,"sequence":437,"environment":429},"fr1\u002Fplant",{"dataset":427,"sequence":439,"environment":429},"fr1\u002Froom",{"dataset":427,"sequence":441,"environment":429},"fr1\u002Frpy",{"dataset":427,"sequence":443,"environment":429},"fr1\u002Fteddy",{"dataset":427,"sequence":445,"environment":429},"fr1\u002Fxyz",{"dataset":427,"sequence":447,"environment":429},"average of 9 fr1 sequences",[449,452,454,456,459,461],{"name":450,"methodId":451,"linkable":155,"proposed":79,"self":79},"ORB-SLAM3 [ 27 ]","orbslam3_2021",{"name":453,"methodId":5,"linkable":155,"proposed":79,"self":155},"DSO [ 12 ]",{"name":455,"methodId":5,"linkable":155,"proposed":79,"self":155},"DSO-Realtime [ 12 ]",{"name":457,"methodId":458,"linkable":155,"proposed":79,"self":79},"DROID-VO [ 37 ]","droidslam2021",{"name":460,"methodId":88,"linkable":79,"proposed":155,"self":79},"Ours (Default)",{"name":462,"methodId":88,"linkable":79,"proposed":155,"self":79},"Ours (Fast)",[464,465,467,468,469,471,472,473,474,476,477,479,481,483,484,486,488,490,491,493,494,496,498,500,502,504,506,507,508,510,511,513,515,517,519,520,522,523,525,527,529,531,533,535,536,537,539,540,542,544,546,547,549,550,552,553,555,556,558,559],[184,184,184,88,184,184,186,186,184],[184,184,188,466,186,184,186,186,184],0.017,[184,184,190,329,186,184,186,186,184],[184,184,193,88,184,184,186,186,184],[184,184,195,470,186,184,186,186,184],0.034,[184,184,198,88,184,184,186,186,184],[184,184,200,88,184,184,186,186,184],[184,184,203,88,184,184,186,186,184],[184,184,206,475,186,184,186,186,184],0.009,[184,184,209,88,188,184,186,186,184],[188,184,184,478,186,184,186,186,184],0.173,[188,184,188,480,186,184,186,186,184],0.567,[188,184,190,482,186,184,186,186,184],0.916,[188,184,193,185,186,184,186,186,184],[188,184,195,485,186,184,186,186,184],0.121,[188,184,198,487,186,184,186,186,184],0.379,[188,184,200,489,186,184,186,186,184],0.058,[188,184,203,88,184,184,186,186,184],[188,184,206,492,186,184,186,186,184],0.036,[188,184,209,88,188,184,186,186,184],[190,184,184,495,186,184,186,186,184],0.172,[190,184,188,497,186,184,186,186,184],0.718,[190,184,190,499,186,184,186,186,184],0.728,[190,184,193,501,186,184,186,186,184],0.068,[190,184,195,503,186,184,186,186,184],0.167,[190,184,198,505,186,184,186,186,184],0.767,[190,184,200,88,184,184,186,186,184],[190,184,203,88,184,184,186,186,184],[190,184,206,509,186,184,186,186,184],0.031,[190,184,209,88,188,184,186,186,184],[193,184,184,512,186,184,186,186,184],0.161,[193,184,188,514,186,184,186,186,184],0.028,[193,184,190,516,186,184,186,186,184],0.099,[193,184,193,518,186,184,186,186,184],0.033,[193,184,195,514,186,184,186,186,184],[193,184,198,521,186,184,186,186,184],0.327,[193,184,200,514,186,184,186,186,184],[193,184,203,524,186,184,186,186,184],0.169,[193,184,206,526,186,184,186,186,184],0.013,[193,184,209,528,186,184,186,186,184],0.098,[195,184,184,530,186,184,186,186,184],0.135,[195,184,188,532,186,184,186,186,184],0.038,[195,184,190,534,186,184,186,186,184],0.048,[195,184,193,191,186,184,186,186,184],[195,184,195,492,186,184,186,186,184],[195,184,198,538,186,184,186,186,184],0.394,[195,184,200,470,186,184,186,186,184],[195,184,203,541,186,184,186,186,184],0.064,[195,184,206,543,186,184,186,186,184],0.012,[195,184,209,545,186,184,186,186,184],0.089,[198,184,184,524,186,184,186,186,184],[198,184,188,548,186,184,186,186,184],0.029,[198,184,190,541,186,184,186,186,184],[198,184,193,551,186,184,186,186,184],0.047,[198,184,195,551,186,184,186,186,184],[198,184,198,554,186,184,186,186,184],0.396,[198,184,200,470,186,184,186,186,184],[198,184,203,557,186,184,186,186,184],0.074,[198,184,206,543,186,184,186,186,184],[198,184,209,560,186,184,186,186,184],0.097,[408,424],[419],[],[],[566],"TUM RGB-D freiburg1 monocular VO, ATE; x = method failed and output no trajectory; '-' = average not computed; median of 5 trials",{"slug":568,"group":569,"sourceId":417,"sourceLabel":418,"table":570,"selfRows":217,"metrics":571,"seqs":574,"entrants":600,"cells":609,"outcomes":730,"locators":731,"hardware":732,"wordings":733,"notes":734},"dpvo2023-table-2","dpvo2023:Table 2","Table 2",[572],{"label":573,"unit":123,"statistic":424,"alignment":125},"ATE[m]",[575,578,580,582,584,586,588,590,592,594,596,598],{"dataset":128,"sequence":576,"environment":577},"MH01","indoor machine hall and Vicon room (MAV)",{"dataset":128,"sequence":579,"environment":577},"MH02",{"dataset":128,"sequence":581,"environment":577},"MH03",{"dataset":128,"sequence":583,"environment":577},"MH04",{"dataset":128,"sequence":585,"environment":577},"MH05",{"dataset":128,"sequence":587,"environment":577},"V101",{"dataset":128,"sequence":589,"environment":577},"V102",{"dataset":128,"sequence":591,"environment":577},"V103",{"dataset":128,"sequence":593,"environment":577},"V201",{"dataset":128,"sequence":595,"environment":577},"V202",{"dataset":128,"sequence":597,"environment":577},"V203",{"dataset":128,"sequence":599,"environment":577},"average of 11 sequences",[601,603,605,606,607,608],{"name":602,"methodId":88,"linkable":79,"proposed":79,"self":79},"TartanVO [ 43 ]",{"name":604,"methodId":116,"linkable":155,"proposed":79,"self":79},"SVO [ 15 ]",{"name":453,"methodId":5,"linkable":155,"proposed":79,"self":155},{"name":457,"methodId":458,"linkable":155,"proposed":79,"self":79},{"name":460,"methodId":88,"linkable":79,"proposed":155,"self":79},{"name":462,"methodId":88,"linkable":79,"proposed":155,"self":79},[610,612,614,616,618,620,622,624,626,628,630,632,633,634,635,636,637,638,639,640,641,642,643,644,646,648,649,650,652,653,654,656,658,660,662,663,665,667,668,670,672,673,675,677,679,681,683,685,687,689,691,692,694,696,697,698,700,702,704,706,708,710,712,714,716,718,720,721,723,724,726,728],[184,184,184,611,186,184,186,186,184],0.639,[184,184,188,613,186,184,186,186,184],0.325,[184,184,190,615,186,184,186,186,184],0.55,[184,184,193,617,186,184,186,186,184],1.153,[184,184,195,619,186,184,186,186,184],1.021,[184,184,198,621,186,184,186,186,184],0.447,[184,184,200,623,186,184,186,186,184],0.389,[184,184,203,625,186,184,186,186,184],0.622,[184,184,206,627,186,184,186,186,184],0.433,[184,184,209,629,186,184,186,186,184],0.749,[184,184,212,631,186,184,186,186,184],1.152,[184,184,215,382,186,184,186,186,184],[188,184,184,201,186,184,186,186,184],[188,184,188,228,186,184,186,186,184],[188,184,190,248,186,184,186,186,184],[188,184,193,244,186,184,186,186,184],[188,184,195,290,186,184,186,186,184],[188,184,198,221,186,184,186,186,184],[188,184,200,329,186,184,186,186,184],[188,184,203,88,184,184,186,186,184],[188,184,206,297,186,184,186,186,184],[188,184,209,297,186,184,186,186,184],[188,184,212,396,186,184,186,186,184],[188,184,215,645,186,184,186,186,184],0.294,[190,184,184,647,186,184,186,186,184],0.046,[190,184,188,647,186,184,186,186,184],[190,184,190,495,186,184,186,186,184],[190,184,193,651,186,184,186,186,184],3.81,[190,184,195,297,186,184,186,186,184],[190,184,198,545,186,184,186,186,184],[190,184,200,655,186,184,186,186,184],0.107,[190,184,203,657,186,184,186,186,184],0.903,[190,184,206,659,186,184,186,186,184],0.044,[190,184,209,661,186,184,186,186,184],0.132,[190,184,212,631,186,184,186,186,184],[190,184,215,664,186,184,186,186,184],0.601,[193,184,184,666,186,184,186,186,184],0.163,[193,184,188,485,186,184,186,186,184],[193,184,190,669,186,184,186,186,184],0.242,[193,184,193,671,186,184,186,186,184],0.399,[193,184,195,225,186,184,186,186,184],[193,184,198,674,186,184,186,186,184],0.103,[193,184,200,676,186,184,186,186,184],0.165,[193,184,203,678,186,184,186,186,184],0.158,[193,184,206,680,186,184,186,186,184],0.102,[193,184,209,682,186,184,186,186,184],0.115,[193,184,212,684,186,184,186,186,184],0.204,[193,184,215,686,186,184,186,186,184],0.186,[195,184,184,688,186,184,186,186,184],0.087,[195,184,188,690,186,184,186,186,184],0.055,[195,184,190,678,186,184,186,186,184],[195,184,193,693,186,184,186,186,184],0.137,[195,184,195,695,186,184,186,186,184],0.114,[195,184,198,213,186,184,186,186,184],[195,184,200,373,186,184,186,186,184],[195,184,203,699,186,184,186,186,184],0.086,[195,184,206,701,186,184,186,186,184],0.057,[195,184,209,703,186,184,186,186,184],0.049,[195,184,212,705,186,184,186,186,184],0.211,[195,184,215,707,186,184,186,186,184],0.105,[198,184,184,709,186,184,186,186,184],0.101,[198,184,188,711,186,184,186,186,184],0.067,[198,184,190,713,186,184,186,186,184],0.177,[198,184,193,715,186,184,186,186,184],0.181,[198,184,195,717,186,184,186,186,184],0.123,[198,184,198,719,186,184,186,186,184],0.053,[198,184,200,678,186,184,186,186,184],[198,184,203,722,186,184,186,186,184],0.095,[198,184,206,722,186,184,186,186,184],[198,184,209,725,186,184,186,186,184],0.063,[198,184,212,727,186,184,186,186,184],0.31,[198,184,215,729,186,184,186,186,184],0.129,[424],[570],[],[],[735],"EuRoC MAV monocular VO, ATE[m] after similarity alignment with EVO (Appendix C); median of 5 runs for DPVO; every other frame skipped",{"slug":737,"group":738,"sourceId":739,"sourceLabel":740,"table":118,"selfRows":215,"metrics":741,"seqs":744,"entrants":769,"cells":777,"outcomes":842,"locators":843,"hardware":844,"wordings":845,"notes":846},"ldso2018-table-i","ldso2018:Table I","ldso2018","Gao et al., 2018",[742],{"label":743,"unit":123,"statistic":424,"alignment":125},"ATE error (m)",[745,749,751,753,755,757,759,761,763,765,767],{"dataset":746,"sequence":747,"environment":748},"KITTI Odometry","00","KITTI Odometry training sequences (platform and scene not described in the paper)",{"dataset":746,"sequence":750,"environment":748},"01",{"dataset":746,"sequence":752,"environment":748},"02",{"dataset":746,"sequence":754,"environment":748},"03",{"dataset":746,"sequence":756,"environment":748},"04",{"dataset":746,"sequence":758,"environment":748},"05",{"dataset":746,"sequence":760,"environment":748},"06",{"dataset":746,"sequence":762,"environment":748},"07",{"dataset":746,"sequence":764,"environment":748},"08",{"dataset":746,"sequence":766,"environment":748},"09",{"dataset":746,"sequence":768,"environment":748},"10",[770,772,774],{"name":771,"methodId":5,"linkable":155,"proposed":79,"self":155},"Mono DSO",{"name":773,"methodId":88,"linkable":79,"proposed":155,"self":79},"LDSO",{"name":775,"methodId":776,"linkable":155,"proposed":79,"self":79},"ORB-SLAM2 (monocular)","orbslam2_2017",[778,780,782,784,786,788,789,791,793,795,797,799,801,802,804,806,808,810,812,814,816,818,820,822,824,826,828,830,832,834,836,838,840],[184,184,184,779,186,184,186,186,184],126.7,[188,184,184,781,186,184,186,186,184],9.322,[190,184,184,783,186,184,186,186,184],8.27,[184,184,188,785,186,184,186,186,184],165.03,[188,184,188,787,186,184,186,186,184],11.68,[190,184,188,88,184,184,186,186,184],[184,184,190,790,186,184,186,186,184],138.7,[188,184,190,792,186,184,186,186,184],31.98,[190,184,190,794,186,184,186,186,184],26.86,[184,184,193,796,186,184,186,186,184],4.77,[188,184,193,798,186,184,186,186,184],2.85,[190,184,193,800,186,184,186,186,184],1.21,[184,184,195,396,186,184,186,186,184],[188,184,195,803,186,184,186,186,184],1.22,[190,184,195,805,186,184,186,186,184],0.77,[184,184,198,807,186,184,186,186,184],49.85,[188,184,198,809,186,184,186,186,184],5.1,[190,184,198,811,186,184,186,186,184],7.91,[184,184,200,813,186,184,186,186,184],113.57,[188,184,200,815,186,184,186,186,184],13.55,[190,184,200,817,186,184,186,186,184],12.54,[184,184,203,819,186,184,186,186,184],27.99,[188,184,203,821,186,184,186,186,184],2.96,[190,184,203,823,186,184,186,186,184],3.44,[184,184,206,825,186,184,186,186,184],120.17,[188,184,206,827,186,184,186,186,184],129.02,[190,184,206,829,186,184,186,186,184],46.81,[184,184,209,831,186,184,186,186,184],74.29,[188,184,209,833,186,184,186,186,184],21.64,[190,184,209,835,186,184,186,186,184],76.54,[184,184,212,837,186,184,186,186,184],16.32,[188,184,212,839,186,184,186,186,184],17.36,[190,184,212,841,186,184,186,186,184],6.61,[408],[118],[],[],[847],"KITTI Odometry training sequences, monocular setting; ATE (m) after Sim(3) alignment to ground truth; x = failure",[849,855,862,867,873,879,884,889,894,900,905,911,917],{"group":850,"slug":851,"sourceLabel":852,"table":419,"selfRows":209,"datasets":853},"nicerslam2024:Table 3","nicerslam2024-table-3","Zhu et al., 2024",[854],"Replica",{"group":856,"slug":857,"sourceLabel":858,"table":859,"selfRows":203,"datasets":860},"d3vo2020:Table 4","d3vo2020-table-4","Yang et al., 2020a","Table 4",[861],"KITTI odometry",{"group":863,"slug":864,"sourceLabel":858,"table":865,"selfRows":200,"datasets":866},"d3vo2020:Table 6","d3vo2020-table-6","Table 6",[99],{"group":868,"slug":869,"sourceLabel":870,"table":871,"selfRows":198,"datasets":872},"deng2026_mcgs_slam:Table 11","deng2026-mcgs-slam-table-11","Deng & Gan, 2026","Table 11",[99],{"group":874,"slug":875,"sourceLabel":876,"table":877,"selfRows":195,"datasets":878},"monogs2024:Table 1","monogs2024-table-1","Matsuki et al., 2024","Table 1",[427],{"group":880,"slug":881,"sourceLabel":418,"table":877,"selfRows":188,"datasets":882},"dpvo2023:Table 1","dpvo2023-table-1",[883],"TartanAir",{"group":885,"slug":886,"sourceLabel":887,"table":419,"selfRows":188,"datasets":888},"dpvslam2024:Table 3","dpvslam2024-table-3","Lipson et al., 2024",[128],{"group":890,"slug":891,"sourceLabel":892,"table":419,"selfRows":188,"datasets":893},"droidslam2021:Table 3","droidslam2021-table-3","Teed & Deng, 2021",[99],{"group":895,"slug":896,"sourceLabel":6,"table":897,"selfRows":188,"datasets":898},"dso2018:Text Sec. 4.1","dso2018-text-sec-4-1","Text Sec. 4.1",[899],"TUM monoVO, EuRoC MAV, ICL-NUIM",{"group":901,"slug":902,"sourceLabel":6,"table":903,"selfRows":188,"datasets":904},"dso2018:Text Sec. 4.2","dso2018-text-sec-4-2","Text Sec. 4.2",[105],{"group":906,"slug":907,"sourceLabel":908,"table":570,"selfRows":188,"datasets":909},"ghadimzadeh2025slamnde:Table 2","ghadimzadeh2025slamnde-table-2","Ghadimzadeh Alamdari et al., 2025",[910],"Luleå SubT tunnel dataset (Koval et al. 2022)",{"group":912,"slug":913,"sourceLabel":740,"table":914,"selfRows":188,"datasets":915},"ldso2018:Table II","ldso2018-table-ii","Table II",[916],"not_reported (average over keyframes)",{"group":918,"slug":919,"sourceLabel":920,"table":914,"selfRows":188,"datasets":921},"orbslam3_2021:Table II","orbslam3-2021-table-ii","Campos et al., 2021",[128],1790510656231]