[{"data":1,"prerenderedAt":1459},["ShallowReactive",2],{"method-besl1992icp":3},{"method":4,"reference":44,"equipment":63,"figures":77,"results":78},{"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":25,"sensors":29,"platform":30,"estimator":31,"association":32,"timeModel":33,"deskew":34,"loopClosure":35,"globalOptimization":36,"mapRepresentation":37,"prior":38,"outputGeometry":39,"compute":40,"codeUrl":41,"codeLicense":42,"relatedVersions":43},"besl1992icp","Besl & McKay, 1992","ICP (point-to-point)","A method for registration of 3-D shapes",1992,"classic","C02","registration_component","迭代最近點（Iterative Closest Point, ICP）將資料形狀分解為點集後，每次迭代先為每一點找模型形狀上的最近點，再以 Horn 的單位四元數封閉解計算最小平方剛體轉換並更新位姿，直到均方誤差的變化小於門檻。作者證明此演算法對均方距離單調收斂至局部極小值，並提出在更新方向一致時以直線或拋物線外插的加速版本，通常可把 50 次以上的迭代縮減為 15 至 20 次。模型可為點集、折線、參數或隱式曲線與曲面及三角網格；全域配準需從多組初始旋轉出發，局部配準另需多組初始平移。作者也指出，資料中若有大量點不對應模型，此方法並不適用，且易受粗大離群值影響。實驗包含合成點集、雜訊曲線與 Bezier 曲面、NRCC 面具雷射三角量測資料及 Tucson 附近的地形資料。","ICP alternates closest-point correspondence and mean-square distance minimization for 6-DoF rigid alignment; it converges monotonically but only to a local minimum, so initialization matters.","full_text_reviewed","peer_reviewed_published","main_body","not_reported（實驗為合成點集、曲線與曲面、NRCC 面具雷射三角量測資料及 Tucson 附近地形資料；主要應用為剛體零件檢測前的模型配準，未涉及營建工地）",[20,21],"simulation","controlled_experiment",[23,24],"[\"handles the full six degrees of freedom and is independent of shape representation (Sec. VII)\", \"no feature extraction, derivative estimation or preprocessing needed when statistical outliers are near zero (Sec. VII)\", \"monotonic convergence theorem","accelerated ICP typically reduces more than 50 basic iterations to 15 or 20 (Sec. IV-B, IV-C)\", \"handles normally distributed vector noise with standard deviation up to 10% of object size in the reported tests (Sec. VII)\", \"relatively insensitive to minor segmentation errors, shown on the African mask parametric model (Sec. VI-C2, VII)\", \"mask registration with 0.59 mm RMS error for all trial positionings (Sec. VI-C2)\"]",[26,27,28],"[\"converges only to the nearest local minimum","global matching relies on a set of initial states (abstract, Sec. V)\", \"not useful when a significant part of the data does not correspond to the model (Sec. V-C)\", \"susceptible to gross statistical outliers unless a robust method is substituted (Sec. VII)\", \"fast quaternion and SVD solves are not easily extended to weighted least squares, so unequal point uncertainties (e.g., navigation laser radars) are not handled (Sec. VII)\", \"local matching becomes costly for small allowable occlusion (about 10% or less) (Sec. VII)\", \"'sea urchin' or 'planet' shapes can defeat any fixed set of initial rotations (Sec. V-B, VII)\", \"does not solve segmentation","intermixed data from two shapes gives wrong registrations (Sec. VII)\"]",[],[],"iterative: closest points, then Horn's closed-form unit-quaternion least-squares registration (preferred over SVD in 2-D and 3-D because reflections are not desired), applied to the original data set, until the mean-square error change falls below a threshold; accelerated variant extrapolates the registration vector by a line or parabola when the last update directions agree within about 10 deg, with v_max = 25 ||dq|| (Sec. III-C, IV-A, IV-C)","closest point on the model shape for each data point; point sets, polylines, triangle sets, parametric and implicit curves and surfaces (parametric entities via a simplex approximation followed by Newton iterations; implicit entities via a simplex approximation plus a constrained Lagrange-multiplier solve, although the implemented system handled implicit surfaces through special cases or parametric forms); O(Np Nx) worst case, O(Np log Nx) average; k-d trees suggested as future speed-up (Sec. III, IV-A, VIII)","not_applicable (pairwise rigid registration)","not_applicable","none","none; global matching by running ICP from a set of initial rotation states (e.g., four states from principal moments when eigenvalues are distinct, or 12, 24, 60 polyhedral group states, 40 or 312 quaternion combinations) and, for local matching, initial translation states (Sec. V-A, V-C)","point sets, curves or surfaces (representation-independent per abstract)","no prior pose for global matching when a sufficient set of initial rotations is used, provided the data covers a significant portion of the model (condition with alpha1 = 1\u002Fsqrt(2)); otherwise an initial pose inside the correct basin is needed (Sec. V-A, V-B)","6-DoF rigid transformation","C programs on a single-processor computer rated at 1.6 Mflops (Linpack 100 x 100); 8 vs 11 points under 1 s; 250 points vs 450 triangles about 3 min (24 rotations); 2546 mask points vs 8442 triangles about 10 min; 13 655 terrain points about 1 hr (Sec. VI)",null,"not_verified",[],{"id":5,"kind":45,"shortName":7,"title":8,"authors":46,"year":9,"venue":49,"venueType":50,"publisher":51,"volumeIssuePages":52,"doi":53,"arxivId":41,"url":54,"firstPublicDate":55,"publicationStatus":16,"metadataStatus":56,"fulltextStatus":15,"era":10,"classicReason":57,"codeUrl":41,"cluster":11,"topics":58,"mdpi":59,"verification":60,"label":6,"fulltextRoute":61,"versionRead":62,"addedByCensus":59},"method",[47,48],"Paul J. Besl","Neil D. McKay","IEEE Transactions on Pattern Analysis and Machine Intelligence","journal","IEEE","14(2):239-256","10.1109\u002F34.121791","https:\u002F\u002Fapi.crossref.org\u002Fworks\u002F10.1109\u002F34.121791","1992-02","metadata_verified","principle reused: the closest-point correspondence plus mean-square distance minimization loop is the base that GICP, VGICP, X-ICP and KISS-ICP-type odometry explicitly build on.",[11],false,"confirmed","NTU institutional (curl)","version of record, IEEE TPAMI 14(2):239-256, February 1992; scanned PDF without a text layer, all 18 pages rendered to images and read visually",[64,71],{"category":65,"model":66,"canonical":66,"role":67,"dataset":68,"specs":69,"locator":70},"other","Hyscan laser triangulation sensor","dataset sensor","NRCC (National Research Council of Canada) African mask range data","commercially available laser triangulation sensor; a low-resolution 64 x 68 gridded image computed from the original data","Sec. VI-C2",{"category":72,"model":73,"canonical":73,"role":74,"dataset":41,"specs":75,"locator":76},"compute","single-processor computer rated at 1.6 Mflops on the 100 x 100 double-precision Linpack benchmark","compute for runtime","all programs written in C","Sec. VI",[],{"totalRows":79,"groupCount":80,"groups":81,"others":1231},262,41,[82,446,726,983],{"slug":83,"group":84,"sourceId":85,"sourceLabel":86,"table":87,"selfRows":88,"metrics":89,"seqs":103,"entrants":147,"cells":154,"outcomes":438,"locators":439,"hardware":442,"wordings":443,"notes":444},"pomerleau2013comparing-table-6","pomerleau2013comparing:Table 6","pomerleau2013comparing","Pomerleau et al., 2013","Table 6",72,[90,94,97,100],{"label":91,"unit":92,"statistic":93,"alignment":34},"translation error A50","m","median",{"label":95,"unit":92,"statistic":96,"alignment":34},"translation error A75","other: 75th percentile (A75)",{"label":98,"unit":92,"statistic":99,"alignment":34},"translation error A95","other: 95th percentile (A95)",{"label":101,"unit":102,"statistic":93,"alignment":34},"rotation error A50","rad",[104,108,110,112,115,117,119,122,124,126,129,131,133,136,138,140,143,145],{"dataset":105,"sequence":106,"environment":107},"Challenging Laser Registration (Pomerleau et al. 2012)","Apartment, EP (easy)","single floor with five rooms (indoor)",{"dataset":105,"sequence":109,"environment":107},"Apartment, MP (medium)",{"dataset":105,"sequence":111,"environment":107},"Apartment, HP (hard)",{"dataset":105,"sequence":113,"environment":114},"Stairs, EP (easy)","small staircase from indoor to outdoor",{"dataset":105,"sequence":116,"environment":114},"Stairs, MP (medium)",{"dataset":105,"sequence":118,"environment":114},"Stairs, HP (hard)",{"dataset":105,"sequence":120,"environment":121},"ETH, EP (easy)","large hallway with pillars and arches",{"dataset":105,"sequence":123,"environment":121},"ETH, MP (medium)",{"dataset":105,"sequence":125,"environment":121},"ETH, HP (hard)",{"dataset":105,"sequence":127,"environment":128},"Gazebo, EP (easy)","gazebo covered by vines in a public park (winter)",{"dataset":105,"sequence":130,"environment":128},"Gazebo, MP (medium)",{"dataset":105,"sequence":132,"environment":128},"Gazebo, HP (hard)",{"dataset":105,"sequence":134,"environment":135},"Wood, EP (easy)","dense vegetation around a small paved way (summer)",{"dataset":105,"sequence":137,"environment":135},"Wood, MP (medium)",{"dataset":105,"sequence":139,"environment":135},"Wood, HP (hard)",{"dataset":105,"sequence":141,"environment":142},"Plain, EP (easy)","small concave basin with alpine vegetation",{"dataset":105,"sequence":144,"environment":142},"Plain, MP (medium)",{"dataset":105,"sequence":146,"environment":142},"Plain, HP (hard)",[148,152],{"name":149,"methodId":150,"linkable":151,"proposed":59,"self":59},"point-to-plane ICP (libpointmatcher baseline, 70% trimmed)","chen1992pointtoplane",true,{"name":153,"methodId":5,"linkable":151,"proposed":59,"self":151},"point-to-point ICP (libpointmatcher baseline, 75% trimmed)",[155,159,162,165,168,170,172,174,176,178,180,182,184,186,188,190,191,193,195,197,199,201,203,205,206,208,210,212,213,215,216,218,220,223,225,227,229,231,233,235,237,240,242,244,246,248,250,252,254,257,259,261,263,264,266,268,270,273,275,277,278,280,282,284,286,289,291,293,295,297,299,301,303,306,308,309,310,312,313,315,317,319,321,323,324,326,328,330,332,335,337,339,341,343,345,347,348,351,353,354,355,357,358,360,361,364,366,368,370,372,374,376,378,380,382,384,386,387,389,391,392,395,396,398,399,401,403,405,406,409,411,413,415,417,419,421,422,425,427,429,431,433,435,437],[156,156,156,157,158,156,158,158,156],0,0.06,-1,[156,160,156,161,158,156,158,158,156],1,0.47,[156,163,156,164,158,156,158,158,156],2,2.11,[156,166,156,167,158,160,158,158,156],3,0.02,[160,156,156,169,158,156,158,158,156],0.13,[160,160,156,171,158,156,158,158,156],0.54,[160,163,156,173,158,156,158,158,156],1.54,[160,166,156,175,158,160,158,158,156],0.07,[156,156,160,177,158,156,158,158,156],0.2,[156,160,160,179,158,156,158,158,156],1.04,[156,163,160,181,158,156,158,158,156],2.98,[156,166,160,183,158,160,158,158,156],0.08,[160,156,160,185,158,156,158,158,156],0.46,[160,160,160,187,158,156,158,158,156],1.03,[160,163,160,189,158,156,158,158,156],2.32,[160,166,160,177,158,160,158,158,156],[156,156,163,192,158,156,158,158,156],1.35,[156,160,163,194,158,156,158,158,156],2.18,[156,163,163,196,158,156,158,158,156],3.66,[156,166,163,198,158,160,158,158,156],1.01,[160,156,163,200,158,156,158,158,156],1.29,[160,160,163,202,158,156,158,158,156],1.99,[160,163,163,204,158,156,158,158,156],3.24,[160,166,163,179,158,160,158,158,156],[156,156,166,207,158,156,158,158,156],0.09,[156,160,166,209,158,156,158,158,156],1.17,[156,163,166,211,158,156,158,158,156],3.49,[156,166,166,167,158,160,158,158,156],[160,156,166,214,158,156,158,158,156],0.35,[160,160,166,200,158,156,158,158,156],[160,163,166,217,158,156,158,158,156],2.57,[160,166,166,219,158,160,158,158,156],0.12,[156,156,221,222,158,156,158,158,156],4,0.61,[156,160,221,224,158,156,158,158,156],2.08,[156,163,221,226,158,156,158,158,156],4.64,[156,166,221,228,158,160,158,158,156],0.16,[160,156,221,230,158,156,158,158,156],0.94,[160,160,221,232,158,156,158,158,156],1.86,[160,163,221,234,158,156,158,158,156],3.38,[160,166,221,236,158,160,158,158,156],0.33,[156,156,238,239,158,156,158,158,156],5,2.05,[156,160,238,241,158,156,158,158,156],3.28,[156,163,238,243,158,156,158,158,156],5.5,[156,166,238,245,158,160,158,158,156],1.48,[160,156,238,247,158,156,158,158,156],1.81,[160,160,238,249,158,156,158,158,156],2.78,[160,163,238,251,158,156,158,158,156],4.75,[160,166,238,253,158,160,158,158,156],1.1,[156,156,255,256,158,156,158,158,156],6,0.1,[156,160,255,258,158,156,158,158,156],0.44,[156,163,255,260,158,156,158,158,156],6.06,[156,166,255,262,158,160,158,158,156],0.01,[160,156,255,161,158,156,158,158,156],[160,160,255,265,158,156,158,158,156],2.23,[160,163,255,267,158,156,158,158,156],6.86,[160,166,255,269,158,160,158,158,156],0.05,[156,156,271,272,158,156,158,158,156],7,0.6,[156,160,271,274,158,156,158,158,156],4.06,[156,163,271,276,158,156,158,158,156],16.3,[156,166,271,262,158,160,158,158,156],[160,156,271,279,158,156,158,158,156],1.92,[160,160,271,281,158,156,158,158,156],4.29,[160,163,271,283,158,156,158,158,156],11.2,[160,166,271,285,158,160,158,158,156],0.14,[156,156,287,288,158,156,158,158,156],8,4.18,[156,160,287,290,158,156,158,158,156],8.55,[156,163,287,292,158,156,158,158,156],19.6,[156,166,287,294,158,160,158,158,156],1.31,[160,156,287,296,158,156,158,158,156],3.84,[160,160,287,298,158,156,158,158,156],7.06,[160,163,287,300,158,156,158,158,156],14.8,[160,166,287,302,158,160,158,158,156],0.97,[156,156,304,305,158,156,158,158,156],9,0.11,[156,160,304,307,158,156,158,158,156],0.38,[156,163,304,224,158,156,158,158,156],[156,166,304,167,158,160,158,158,156],[160,156,304,311,158,156,158,158,156],0.28,[160,160,304,272,158,156,158,158,156],[160,163,304,314,158,156,158,158,156],1.71,[160,166,304,316,158,160,158,158,156],0.04,[156,156,318,311,158,156,158,158,156],10,[156,160,318,320,158,156,158,158,156],0.96,[156,163,318,322,158,156,158,158,156],3.51,[156,166,318,316,158,160,158,158,156],[160,156,318,325,158,156,158,158,156],0.49,[160,160,318,327,158,156,158,158,156],1.13,[160,163,318,329,158,156,158,158,156],3.18,[160,166,318,331,158,160,158,158,156],0.15,[156,156,333,334,158,156,158,158,156],11,1.87,[156,160,333,336,158,156,158,158,156],3.33,[156,163,333,338,158,156,158,158,156],6.95,[156,166,333,340,158,160,158,158,156],0.58,[160,156,333,342,158,156,158,158,156],1.58,[160,160,333,344,158,156,158,158,156],2.79,[160,163,333,346,158,156,158,158,156],4.57,[160,166,333,340,158,160,158,158,156],[156,156,349,350,158,156,158,158,156],12,0.25,[156,160,349,352,158,156,158,158,156],1.55,[156,163,349,251,158,156,158,158,156],[156,166,349,269,158,160,158,158,156],[160,156,349,356,158,156,158,158,156],0.39,[160,160,349,245,158,156,158,158,156],[160,163,349,359,158,156,158,158,156],4.21,[160,166,349,207,158,160,158,158,156],[156,156,362,363,158,156,158,158,156],13,1.25,[156,160,362,365,158,156,158,158,156],2.92,[156,163,362,367,158,156,158,158,156],6.62,[156,166,362,369,158,160,158,158,156],0.31,[160,156,362,371,158,156,158,158,156],1.19,[160,160,362,373,158,156,158,158,156],2.52,[160,163,362,375,158,156,158,158,156],5.15,[160,166,362,377,158,160,158,158,156],0.32,[156,156,379,344,158,156,158,158,156],14,[156,160,379,381,158,156,158,158,156],4.52,[156,163,379,383,158,156,158,158,156],7.86,[156,166,379,385,158,160,158,158,156],1.05,[160,156,379,189,158,156,158,158,156],[160,160,379,388,158,156,158,158,156],3.73,[160,163,379,390,158,156,158,158,156],6.82,[160,166,379,302,158,160,158,158,156],[156,156,393,394,158,156,158,158,156],15,0.42,[156,160,393,173,158,156,158,158,156],[156,163,393,397,158,156,158,158,156],4.15,[156,166,393,175,158,160,158,158,156],[160,156,393,400,158,156,158,158,156],0.51,[160,160,393,402,158,156,158,158,156],1.46,[160,163,393,404,158,156,158,158,156],3.09,[160,166,393,207,158,160,158,158,156],[156,156,407,408,158,156,158,158,156],16,1.3,[156,160,407,410,158,156,158,158,156],2.58,[156,163,407,412,158,156,158,158,156],5.58,[156,166,407,414,158,160,158,158,156],0.19,[160,156,407,416,158,156,158,158,156],1.21,[160,160,407,418,158,156,158,158,156],2.17,[160,163,407,420,158,156,158,158,156],3.76,[160,166,407,177,158,160,158,158,156],[156,156,423,424,158,156,158,158,156],17,2.35,[156,160,423,426,158,156,158,158,156],4.13,[156,163,423,428,158,156,158,158,156],8.85,[156,166,423,430,158,160,158,158,156],0.5,[160,156,423,432,158,156,158,158,156],2.02,[160,160,423,434,158,156,158,158,156],3.14,[160,163,423,436,158,156,158,158,156],6.33,[160,166,423,185,158,160,158,158,156],[],[440,441],"Table 6 (top)","Table 6 (bottom)",[],[],[445],"35 scan pairs per data set (overlap 0.30 to 0.99) with 64 Gaussian perturbations per level (EP easy, MP medium, HP hard); errors after registration against theodolite ground truth: translation = Euclidean norm (m), rotation = geodesic angle (rad); A50\u002FA75\u002FA95 quantiles",{"slug":447,"group":448,"sourceId":449,"sourceLabel":450,"table":451,"selfRows":452,"metrics":453,"seqs":461,"entrants":488,"cells":510,"outcomes":720,"locators":721,"hardware":722,"wordings":723,"notes":724},"vizzo2021puma-table-ii","vizzo2021puma:Table II","vizzo2021puma","Vizzo et al., 2021","Table II",26,[454,458],{"label":455,"unit":456,"statistic":457,"alignment":35},"relative translational error (%)","%","mean",{"label":459,"unit":460,"statistic":457,"alignment":35},"relative rotational error (deg per 100 m)","deg\u002F100 m",[462,466,468,470,472,474,476,478,480,482,484,486],{"dataset":463,"sequence":464,"environment":465},"KITTI Odometry","average of 00-10","outdoor driving (urban, country, highway)",{"dataset":463,"sequence":467,"environment":465},"00",{"dataset":463,"sequence":469,"environment":465},"01",{"dataset":463,"sequence":471,"environment":465},"02",{"dataset":463,"sequence":473,"environment":465},"03",{"dataset":463,"sequence":475,"environment":465},"04",{"dataset":463,"sequence":477,"environment":465},"05",{"dataset":463,"sequence":479,"environment":465},"06",{"dataset":463,"sequence":481,"environment":465},"07",{"dataset":463,"sequence":483,"environment":465},"08",{"dataset":463,"sequence":485,"environment":465},"09",{"dataset":463,"sequence":487,"environment":465},"10",[489,491,494,497,500,502,504,506,508],{"name":490,"methodId":5,"linkable":151,"proposed":59,"self":151},"point-to-point ICP [3] (map: None, DA: NN)",{"name":492,"methodId":493,"linkable":59,"proposed":59,"self":59},"point-to-plane ICP [32] (map: None, DA: NN)","rusinkiewicz2001variants",{"name":495,"methodId":496,"linkable":151,"proposed":59,"self":59},"GICP [33] (map: None, DA: NN)","segal2009gicp",{"name":498,"methodId":499,"linkable":151,"proposed":59,"self":59},"SuMa [1] (map: None, DA: Proj.)","suma2018",{"name":501,"methodId":5,"linkable":151,"proposed":59,"self":151},"point-to-point ICP [3] (map: Point cloud, DA: NN)",{"name":503,"methodId":493,"linkable":59,"proposed":59,"self":59},"point-to-plane ICP [32] (map: Point cloud, DA: NN)",{"name":505,"methodId":496,"linkable":151,"proposed":59,"self":59},"GICP [33] (map: Point cloud, DA: NN)",{"name":507,"methodId":449,"linkable":151,"proposed":59,"self":59},"Ours (Δtree = 10) (map: Mesh, DA: NN)",{"name":509,"methodId":449,"linkable":151,"proposed":151,"self":59},"Ours (Δtree = 10) (map: Mesh, DA: RC)",[511,513,515,517,519,521,523,524,526,528,530,531,532,533,535,537,538,540,542,544,546,548,550,552,554,556,557,559,561,563,565,566,568,570,571,573,575,577,578,580,582,584,586,588,590,592,593,595,597,599,600,601,603,605,607,609,611,612,614,615,617,619,621,622,623,625,627,629,631,633,635,637,639,641,643,645,647,649,651,653,655,657,659,661,663,665,667,668,670,672,674,676,678,679,681,683,685,686,687,689,691,693,695,696,698,699,700,701,702,704,706,708,710,712,714,716,718],[156,156,156,512,158,156,158,158,156],4.86,[156,156,160,514,158,156,158,158,156],3.65,[156,156,163,516,158,156,158,158,156],15.4,[156,156,166,518,158,156,158,158,156],4.6,[156,156,221,520,158,156,158,158,156],5.74,[156,156,238,522,158,156,158,158,156],2.44,[156,156,255,234,158,156,158,158,156],[156,156,271,525,158,156,158,158,156],2.94,[156,156,287,527,158,156,158,158,156],4.92,[156,156,304,529,158,156,158,158,156],3.75,[156,156,318,234,158,156,158,158,156],[156,156,333,204,158,156,158,158,156],[156,160,156,314,158,156,158,158,156],[160,156,156,534,158,156,158,158,156],7.6,[160,156,160,536,158,156,158,158,156],9.12,[160,156,163,318,158,156,158,158,156],[160,156,166,539,158,156,158,158,156],6.19,[160,156,221,541,158,156,158,158,156],6.04,[160,156,238,543,158,156,158,158,156],4.51,[160,156,255,545,158,156,158,158,156],7.69,[160,156,271,547,158,156,158,158,156],8.24,[160,156,287,549,158,156,158,158,156],5.53,[160,156,304,551,158,156,158,158,156],8.7,[160,156,318,553,158,156,158,158,156],9.37,[160,156,333,555,158,156,158,158,156],8.18,[160,160,156,211,158,156,158,158,156],[163,156,156,558,158,156,158,158,156],14.35,[163,156,160,560,158,156,158,158,156],7.35,[163,156,163,562,158,156,158,158,156],73.1,[163,156,166,564,158,156,158,158,156],14.4,[163,156,221,553,158,156,158,158,156],[163,156,238,567,158,156,158,158,156],13.6,[163,156,255,569,158,156,158,158,156],5.23,[163,156,271,265,158,156,158,158,156],[163,156,287,572,158,156,158,158,156],6.4,[163,156,304,574,158,156,158,158,156],7.27,[163,156,318,576,158,156,158,158,156],10.9,[163,156,333,287,158,156,158,158,156],[163,160,156,579,158,156,158,158,156],4.78,[166,156,156,581,158,156,158,158,156],2.93,[166,156,160,583,158,156,158,158,156],2.09,[166,156,163,585,158,156,158,158,156],4.05,[166,156,166,587,158,156,158,158,156],2.3,[166,156,221,589,158,156,158,158,156],1.43,[166,156,238,591,158,156,158,158,156],11.9,[166,156,255,402,158,156,158,158,156],[166,156,271,594,158,156,158,158,156],0.95,[166,156,287,596,158,156,158,158,156],1.75,[166,156,304,598,158,156,158,158,156],2.53,[166,156,318,279,158,156,158,158,156],[166,156,333,247,158,156,158,158,156],[166,160,156,602,158,156,158,158,156],0.92,[221,156,156,604,158,156,158,158,156],29.98,[221,156,160,606,158,156,158,158,156],9.25,[221,156,163,608,158,156,158,158,156],93.2,[221,156,166,610,158,156,158,158,156],30.4,[221,156,221,576,158,156,158,158,156],[221,156,238,613,158,156,158,158,156],91.4,[221,156,255,602,158,156,158,158,156],[221,156,271,616,158,156,158,158,156],33.9,[221,156,287,618,158,156,158,158,156],8.35,[221,156,304,620,158,156,158,158,156],2.81,[221,156,318,616,158,156,158,158,156],[221,156,333,300,158,156,158,158,156],[221,160,156,624,158,156,158,158,156],2.61,[238,156,156,626,158,156,158,158,156],18.92,[238,156,160,628,158,156,158,158,156],9.99,[238,156,163,630,158,156,158,158,156],77.1,[238,156,166,632,158,156,158,158,156],11.7,[238,156,221,634,158,156,158,158,156],2.31,[238,156,238,636,158,156,158,158,156],70,[238,156,255,638,158,156,158,158,156],2.62,[238,156,271,640,158,156,158,158,156],1.84,[238,156,287,642,158,156,158,158,156],1.79,[238,156,304,644,158,156,158,158,156],3.67,[238,156,318,646,158,156,158,158,156],17.4,[238,156,333,648,158,156,158,158,156],9.7,[238,160,156,650,158,156,158,158,156],4.01,[255,156,156,652,158,156,158,158,156],20.43,[255,156,160,654,158,156,158,158,156],4.34,[255,156,163,656,158,156,158,158,156],93.1,[255,156,166,658,158,156,158,158,156],10.7,[255,156,221,660,158,156,158,158,156],2.21,[255,156,238,662,158,156,158,158,156],83.7,[255,156,255,664,158,156,158,158,156],1.56,[255,156,271,666,158,156,158,158,156],1.42,[255,156,287,371,158,156,158,158,156],[255,156,304,669,158,156,158,158,156],2.33,[255,156,318,671,158,156,158,158,156],21.8,[255,156,333,673,158,156,158,158,156],2.37,[255,160,156,675,158,156,158,158,156],2.76,[271,156,156,677,158,156,158,158,156],2.15,[271,156,160,434,158,156,158,158,156],[271,156,163,680,158,156,158,158,156],4.32,[271,156,166,682,158,156,158,158,156],1.91,[271,156,221,684,158,156,158,158,156],1.34,[271,156,238,583,158,156,158,158,156],[271,156,255,664,158,156,158,158,156],[271,156,271,688,158,156,158,158,156],1.41,[271,156,287,690,158,156,158,158,156],1.88,[271,156,304,692,158,156,158,158,156],1.97,[271,156,318,694,158,156,158,158,156],1.8,[271,156,333,660,158,156,158,158,156],[271,160,156,697,158,156,158,158,156],1.14,[287,156,156,352,158,156,158,158,156],[287,156,160,402,158,156,158,158,156],[287,156,163,234,158,156,158,158,156],[287,156,166,232,158,156,158,158,156],[287,156,221,703,158,156,158,158,156],1.6,[287,156,238,705,158,156,158,158,156],1.63,[287,156,255,707,158,156,158,158,156],1.2,[287,156,271,709,158,156,158,158,156],0.88,[287,156,287,711,158,156,158,158,156],0.72,[287,156,304,713,158,156,158,158,156],1.44,[287,156,318,715,158,156,158,158,156],1.51,[287,156,333,717,158,156,158,158,156],1.38,[287,160,156,719,158,156,158,158,156],0.74,[],[451],[],[],[725],"KITTI odometry training sequences 00-10; relative errors averaged over 100-800 m segments; all methods share the range-image normals and Huber loss; Map None = frame-to-frame, Map Point cloud = frame-to-model on the last N scans; DA = data association (NN nearest neighbour, Proj. projective, RC ray casting). Per-sequence rotational errors omitted to respect the row cap; only the rotational average is kept",{"slug":727,"group":728,"sourceId":729,"sourceLabel":730,"table":731,"selfRows":407,"metrics":732,"seqs":738,"entrants":759,"cells":777,"outcomes":976,"locators":978,"hardware":979,"wordings":980,"notes":981},"lonet2019-table-1","lonet2019:Table 1","lonet2019","Li et al., 2019","Table 1",[733,735],{"label":734,"unit":456,"statistic":457,"alignment":35},"t_rel: average translational RMSE (%) on length of 100 m-800 m",{"label":736,"unit":737,"statistic":457,"alignment":35},"r_rel: average rotational RMSE (deg\u002F100 m) on length of 100 m-800 m","deg\u002F100m",[739,743,745,747,749,751,753,757],{"dataset":740,"sequence":741,"environment":742},"KITTI odometry","07 (not used for training)","urban, country and highway driving, vehicle-mounted Velodyne HDL-64",{"dataset":740,"sequence":744,"environment":742},"08 (not used for training)",{"dataset":740,"sequence":746,"environment":742},"09 (not used for training)",{"dataset":740,"sequence":748,"environment":742},"10 (not used for training)",{"dataset":740,"sequence":750,"environment":742},"mean over 00-06 (training sequences)",{"dataset":740,"sequence":752,"environment":742},"mean over 07-10 (test sequences)",{"dataset":754,"sequence":755,"environment":756},"Ford Campus Vision and Lidar","Ford-1","urban campus driving with many moving vehicles, roof-mounted lidar",{"dataset":754,"sequence":758,"environment":756},"Ford-2",[760,762,764,766,768,771,773,775],{"name":761,"methodId":5,"linkable":151,"proposed":59,"self":151},"ICP-po2po (PCL)",{"name":763,"methodId":150,"linkable":151,"proposed":59,"self":59},"ICP-po2pl (PCL)",{"name":765,"methodId":496,"linkable":151,"proposed":59,"self":59},"GICP [30]",{"name":767,"methodId":41,"linkable":59,"proposed":59,"self":59},"CLS [34]",{"name":769,"methodId":770,"linkable":151,"proposed":59,"self":59},"LOAM [45] (authors' modified re-run)","loam2017_auro",{"name":772,"methodId":41,"linkable":59,"proposed":59,"self":59},"Velas et al. [35] (values from [35])",{"name":774,"methodId":729,"linkable":151,"proposed":151,"self":59},"LO-Net",{"name":776,"methodId":729,"linkable":151,"proposed":151,"self":59},"LO-Net+Mapping",[778,780,782,784,786,788,790,792,794,796,798,800,802,804,806,808,810,811,812,814,816,818,819,821,823,824,825,826,827,828,830,832,834,836,838,839,841,842,844,845,847,848,850,851,853,855,856,858,860,861,863,864,865,867,868,870,872,873,875,876,877,879,881,883,884,886,887,889,890,891,893,894,896,897,898,900,901,903,904,906,907,909,910,911,912,914,915,917,918,920,921,923,924,925,926,927,928,930,932,934,935,937,938,939,941,943,945,946,948,950,951,952,954,956,957,959,961,962,963,964,966,968,969,971,972,973,974,975],[156,156,156,779,158,156,158,158,156],5.17,[156,160,156,781,158,156,158,158,156],3.35,[156,156,160,783,158,156,158,158,156],10.04,[156,160,160,785,158,156,158,158,156],4.93,[156,156,163,787,158,156,158,158,156],6.93,[156,160,163,789,158,156,158,158,156],2.89,[156,156,166,791,158,156,158,158,156],8.91,[156,160,166,793,158,156,158,158,156],4.74,[156,156,221,795,158,156,158,158,156],7.13,[156,160,221,797,158,156,158,158,156],3.08,[156,156,238,799,158,156,158,158,156],7.76,[156,160,238,801,158,156,158,158,156],3.98,[156,156,255,803,158,156,158,158,156],8.2,[156,160,255,805,158,156,158,158,156],2.64,[156,156,271,807,158,156,158,158,156],16.23,[156,160,271,809,158,156,158,158,156],2.84,[160,156,156,352,158,156,158,158,156],[160,160,156,666,158,156,158,158,156],[160,156,160,813,158,156,158,158,156],4.42,[160,160,160,815,158,156,158,158,156],2.14,[160,156,163,817,158,156,158,158,156],3.95,[160,160,163,314,158,156,158,158,156],[160,156,166,820,158,156,158,158,156],6.13,[160,160,166,822,158,156,158,158,156],2.6,[160,156,221,375,158,156,158,158,156],[160,160,221,682,158,156,158,158,156],[160,156,238,650,158,156,158,158,156],[160,160,238,692,158,156,158,158,156],[160,156,255,781,158,156,158,158,156],[160,160,255,829,158,156,158,158,156],1.65,[160,156,271,831,158,156,158,158,156],5.68,[160,160,271,833,158,156,158,158,156],1.96,[163,156,156,835,158,156,158,158,156],0.64,[163,160,156,837,158,156,158,158,156],0.45,[163,156,160,342,158,156,158,158,156],[163,160,160,840,158,156,158,158,156],0.75,[163,156,163,692,158,156,158,158,156],[163,160,163,843,158,156,158,158,156],0.77,[163,156,166,294,158,156,158,158,156],[163,160,166,846,158,156,158,158,156],0.62,[163,156,221,265,158,156,158,158,156],[163,160,221,849,158,156,158,158,156],0.78,[163,156,238,717,158,156,158,158,156],[163,160,238,852,158,156,158,158,156],0.65,[163,156,255,854,158,156,158,158,156],3.07,[163,160,255,209,158,156,158,158,156],[163,156,271,857,158,156,158,158,156],5.11,[163,160,271,859,158,156,158,158,156],1.47,[166,156,156,179,158,156,158,158,156],[166,160,156,862,158,156,158,158,156],0.73,[166,156,160,815,158,156,158,158,156],[166,160,160,385,158,156,158,158,156],[166,156,163,866,158,156,158,158,156],1.95,[166,160,163,602,158,156,158,158,156],[166,156,166,869,158,156,158,158,156],3.46,[166,160,166,871,158,156,158,158,156],1.28,[166,156,221,164,158,156,158,158,156],[166,160,221,874,158,156,158,158,156],0.86,[166,156,238,677,158,156,158,158,156],[166,160,238,160,158,156,158,158,156],[166,156,255,878,158,156,158,158,156],10.54,[166,160,255,880,158,156,158,158,156],3.9,[166,156,271,882,158,156,158,158,156],14.78,[166,160,271,518,158,156,158,158,156],[221,156,156,885,158,156,158,158,156],0.69,[221,160,156,430,158,156,158,158,156],[221,156,160,888,158,156,158,158,156],1.18,[221,160,160,258,158,156,158,158,156],[221,156,163,707,158,156,158,158,156],[221,160,163,892,158,156,158,158,156],0.48,[221,156,166,715,158,156,158,158,156],[221,160,166,895,158,156,158,158,156],0.57,[221,156,221,192,158,156,158,158,156],[221,160,221,400,158,156,158,158,156],[221,156,238,899,158,156,158,158,156],1.15,[221,160,238,430,158,156,158,158,156],[221,156,255,902,158,156,158,158,156],1.68,[221,160,255,171,158,156,158,158,156],[221,156,271,905,158,156,158,158,156],1.78,[221,160,271,325,158,156,158,158,156],[238,156,156,908,158,156,158,158,156],1.77,[238,160,156,41,156,156,158,158,156],[238,156,160,789,158,156,158,158,156],[238,160,160,41,156,156,158,158,156],[238,156,163,913,158,156,158,158,156],4.94,[238,160,163,41,156,156,158,158,156],[238,156,166,916,158,156,158,158,156],3.27,[238,160,166,41,156,156,158,158,156],[238,156,221,919,158,156,158,158,156],3.12,[238,160,221,41,156,156,158,158,156],[238,156,238,922,158,156,158,158,156],3.22,[238,160,238,41,156,156,158,158,156],[238,156,255,41,156,156,158,158,156],[238,160,255,41,156,156,158,158,156],[238,156,271,41,156,156,158,158,156],[238,160,271,41,156,156,158,158,156],[255,156,156,929,158,156,158,158,156],1.7,[255,160,156,931,158,156,158,158,156],0.89,[255,156,160,933,158,156,158,158,156],2.12,[255,160,160,843,158,156,158,158,156],[255,156,163,936,158,156,158,158,156],1.37,[255,160,163,340,158,156,158,158,156],[255,156,166,694,158,156,158,158,156],[255,160,166,940,158,156,158,158,156],0.93,[255,156,221,942,158,156,158,158,156],1.09,[255,160,221,944,158,156,158,158,156],0.63,[255,156,238,596,158,156,158,158,156],[255,160,238,947,158,156,158,158,156],0.79,[255,156,255,949,158,156,158,158,156],2.27,[255,160,255,846,158,156,158,158,156],[255,156,271,194,158,156,158,158,156],[255,160,271,953,158,156,158,158,156],0.59,[271,156,156,955,158,156,158,158,156],0.56,[271,160,156,837,158,156,158,158,156],[271,156,160,958,158,156,158,158,156],1.08,[271,160,160,960,158,156,158,158,156],0.43,[271,156,163,843,158,156,158,158,156],[271,160,163,307,158,156,158,158,156],[271,156,166,602,158,156,158,158,156],[271,160,166,965,158,156,158,158,156],0.41,[271,156,221,967,158,156,158,158,156],0.81,[271,160,221,258,158,156,158,158,156],[271,156,238,970,158,156,158,158,156],0.83,[271,160,238,394,158,156,158,158,156],[271,156,255,253,158,156,158,158,156],[271,160,255,430,158,156,158,158,156],[271,156,271,200,158,156,158,158,156],[271,160,271,258,158,156,158,158,156],[977],"not_reported (NA)",[731],[],[],[982],"KITTI odometry metric: t_rel = average translational RMSE (%) and r_rel = average rotational RMSE (deg\u002F100 m) over 100-800 m lengths. LO-Net trained on KITTI 00-06 and tested on 07-10 and on Ford without fine-tuning; loop closure disabled for all methods. LOAM values outside brackets come from the authors' modified re-run; bracketed values are quoted from the LOAM paper [45]. Velas et al. values quoted from [35] (r_rel and Ford NA). ICP variants run with PCL. Truncated: per-sequence rows 00-06 (training sequences) omitted; the mean over them (mean-dagger) is kept.",{"slug":984,"group":985,"sourceId":986,"sourceLabel":987,"table":731,"selfRows":362,"metrics":988,"seqs":996,"entrants":1022,"cells":1044,"outcomes":1225,"locators":1226,"hardware":1227,"wordings":1228,"notes":1229},"pwclonet2021-table-1","pwclonet2021:Table 1","pwclonet2021","Wang et al., 2021c",[989,992,994],{"label":990,"unit":456,"statistic":991,"alignment":34},"trel (average translational RMSE, %)","RMSE",{"label":993,"unit":456,"statistic":991,"alignment":34},"Mean on 07-10, trel",{"label":995,"unit":737,"statistic":991,"alignment":34},"Mean on 07-10, rrel (deg\u002F100m)",[997,1000,1002,1004,1006,1008,1010,1012,1014,1016,1018,1020],{"dataset":740,"sequence":998,"environment":999},"00* (training)","vehicle, road",{"dataset":740,"sequence":1001,"environment":999},"01* (training)",{"dataset":740,"sequence":1003,"environment":999},"02* (training)",{"dataset":740,"sequence":1005,"environment":999},"03* (training)",{"dataset":740,"sequence":1007,"environment":999},"04* (training)",{"dataset":740,"sequence":1009,"environment":999},"05* (training)",{"dataset":740,"sequence":1011,"environment":999},"06* (training)",{"dataset":740,"sequence":1013,"environment":999},"07 (test)",{"dataset":740,"sequence":1015,"environment":999},"08 (test)",{"dataset":740,"sequence":1017,"environment":999},"09 (test)",{"dataset":740,"sequence":1019,"environment":999},"10 (test)",{"dataset":740,"sequence":1021,"environment":999},"mean on 07-10 (test)",[1023,1025,1027,1029,1031,1033,1035,1037,1039,1042],{"name":1024,"methodId":770,"linkable":151,"proposed":59,"self":59},"Full LOAM [31]",{"name":1026,"methodId":5,"linkable":151,"proposed":59,"self":151},"ICP-po2po",{"name":1028,"methodId":150,"linkable":151,"proposed":59,"self":59},"ICP-po2pl",{"name":1030,"methodId":496,"linkable":151,"proposed":59,"self":59},"GICP [19]",{"name":1032,"methodId":41,"linkable":59,"proposed":59,"self":59},"CLS [21]",{"name":1034,"methodId":41,"linkable":59,"proposed":59,"self":59},"Velas et al. [22]",{"name":1036,"methodId":729,"linkable":151,"proposed":59,"self":59},"LO-Net [10]",{"name":1038,"methodId":41,"linkable":59,"proposed":59,"self":59},"DMLO [11]",{"name":1040,"methodId":1041,"linkable":151,"proposed":59,"self":59},"LOAM w\u002Fo mapping (published code run by authors)","loam2014",{"name":1043,"methodId":986,"linkable":151,"proposed":151,"self":59},"Ours (PWCLO-Net)",[1045,1046,1047,1048,1049,1051,1052,1053,1054,1055,1056,1057,1059,1061,1063,1065,1067,1069,1071,1073,1074,1075,1076,1077,1078,1080,1082,1084,1086,1087,1089,1091,1093,1094,1095,1096,1097,1098,1100,1102,1103,1105,1106,1107,1108,1110,1111,1112,1113,1114,1115,1117,1119,1120,1122,1123,1124,1126,1128,1129,1130,1131,1132,1133,1135,1137,1139,1141,1143,1144,1145,1146,1147,1148,1149,1150,1151,1153,1154,1156,1158,1159,1160,1161,1163,1164,1165,1166,1167,1169,1171,1172,1173,1174,1176,1178,1180,1182,1184,1186,1188,1190,1192,1193,1195,1197,1199,1201,1203,1205,1206,1208,1209,1211,1213,1214,1216,1217,1219,1220,1222,1224],[156,156,156,253,158,156,158,158,156],[156,156,160,344,158,156,158,158,156],[156,156,163,173,158,156,158,158,156],[156,156,166,327,158,156,158,158,156],[156,156,221,1050,158,156,158,158,156],1.45,[156,156,238,840,158,156,158,158,156],[156,156,255,711,158,156,158,158,156],[156,156,271,885,158,156,158,158,156],[156,156,287,888,158,156,158,158,156],[156,156,304,707,158,156,158,158,156],[156,156,318,715,158,156,158,158,156],[156,160,333,1058,158,156,158,158,156],1.145,[156,163,333,1060,158,156,158,158,156],0.498,[160,156,156,1062,158,156,158,158,156],6.88,[160,156,160,1064,158,156,158,158,156],11.21,[160,156,163,1066,158,156,158,158,156],8.21,[160,156,166,1068,158,156,158,158,156],11.07,[160,156,221,1070,158,156,158,158,156],6.64,[160,156,238,1072,158,156,158,158,156],3.97,[160,156,255,866,158,156,158,158,156],[160,156,271,779,158,156,158,158,156],[160,156,287,783,158,156,158,158,156],[160,156,304,787,158,156,158,158,156],[160,156,318,791,158,156,158,158,156],[160,160,333,1079,158,156,158,158,156],7.763,[160,163,333,1081,158,156,158,158,156],3.978,[163,156,156,1083,158,156,158,158,156],3.8,[163,156,160,1085,158,156,158,158,156],13.53,[163,156,163,304,158,156,158,158,156],[163,156,166,1088,158,156,158,158,156],2.72,[163,156,221,1090,158,156,158,158,156],2.96,[163,156,238,1092,158,156,158,158,156],2.29,[163,156,255,908,158,156,158,158,156],[163,156,271,352,158,156,158,158,156],[163,156,287,813,158,156,158,158,156],[163,156,304,817,158,156,158,158,156],[163,156,318,820,158,156,158,158,156],[163,160,333,1099,158,156,158,158,156],4.013,[163,163,333,1101,158,156,158,158,156],1.968,[166,156,156,200,158,156,158,158,156],[166,156,160,1104,158,156,158,158,156],4.39,[166,156,163,598,158,156,158,158,156],[166,156,166,902,158,156,158,158,156],[166,156,221,420,158,156,158,158,156],[166,156,238,1109,158,156,158,158,156],1.02,[166,156,255,602,158,156,158,158,156],[166,156,271,835,158,156,158,158,156],[166,156,287,342,158,156,158,158,156],[166,156,304,692,158,156,158,158,156],[166,156,318,294,158,156,158,158,156],[166,160,333,1116,158,156,158,158,156],1.375,[166,163,333,1118,158,156,158,158,156],0.648,[221,156,156,164,158,156,158,158,156],[221,156,160,1121,158,156,158,158,156],4.22,[221,156,163,1092,158,156,158,158,156],[221,156,166,705,158,156,158,158,156],[221,156,221,1125,158,156,158,158,156],1.59,[221,156,238,1127,158,156,158,158,156],1.98,[221,156,255,602,158,156,158,158,156],[221,156,271,179,158,156,158,158,156],[221,156,287,815,158,156,158,158,156],[221,156,304,866,158,156,158,158,156],[221,156,318,869,158,156,158,158,156],[221,160,333,1134,158,156,158,158,156],2.148,[221,163,333,1136,158,156,158,158,156],0.995,[238,156,156,1138,158,156,158,158,156],3.02,[238,156,160,1140,158,156,158,158,156],4.44,[238,156,163,1142,158,156,158,158,156],3.42,[238,156,166,913,158,156,158,158,156],[238,156,221,908,158,156,158,158,156],[238,156,238,424,158,156,158,158,156],[238,156,255,690,158,156,158,158,156],[238,156,271,908,158,156,158,158,156],[238,156,287,789,158,156,158,158,156],[238,156,304,913,158,156,158,158,156],[238,156,318,916,158,156,158,158,156],[238,160,333,1152,158,156,158,158,156],3.218,[255,156,156,859,158,156,158,158,156],[255,156,160,1155,158,156,158,158,156],1.36,[255,156,163,1157,158,156,158,158,156],1.52,[255,156,166,187,158,156,158,158,156],[255,156,221,400,158,156,158,158,156],[255,156,238,179,158,156,158,158,156],[255,156,255,1162,158,156,158,158,156],0.71,[255,156,271,929,158,156,158,158,156],[255,156,287,933,158,156,158,158,156],[255,156,304,936,158,156,158,158,156],[255,156,318,694,158,156,158,158,156],[255,160,333,1168,158,156,158,158,156],1.748,[255,163,333,1170,158,156,158,158,156],0.793,[271,156,271,862,158,156,158,158,156],[271,156,287,958,158,156,158,158,156],[271,156,304,253,158,156,158,158,156],[271,156,318,1175,158,156,158,158,156],1.12,[271,160,333,1177,158,156,158,158,156],1.008,[271,163,333,1179,158,156,158,158,156],0.538,[287,156,156,1181,158,156,158,158,156],15.99,[287,156,160,1183,158,156,158,158,156],3.43,[287,156,163,1185,158,156,158,158,156],9.4,[287,156,166,1187,158,156,158,158,156],18.18,[287,156,221,1189,158,156,158,158,156],9.59,[287,156,238,1191,158,156,158,158,156],9.16,[287,156,255,791,158,156,158,158,156],[287,156,271,1194,158,156,158,158,156],10.87,[287,156,287,1196,158,156,158,158,156],12.72,[287,156,304,1198,158,156,158,158,156],8.1,[287,156,318,1200,158,156,158,158,156],12.67,[287,160,333,1202,158,156,158,158,156],11.09,[287,163,333,1204,158,156,158,158,156],6.405,[304,156,156,849,158,156,158,158,156],[304,156,160,1207,158,156,158,158,156],0.67,[304,156,163,874,158,156,158,158,156],[304,156,166,1210,158,156,158,158,156],0.76,[304,156,221,1212,158,156,158,158,156],0.37,[304,156,238,837,158,156,158,158,156],[304,156,255,1215,158,156,158,158,156],0.27,[304,156,271,272,158,156,158,158,156],[304,156,287,1218,158,156,158,158,156],1.26,[304,156,304,947,158,156,158,158,156],[304,156,318,1221,158,156,158,158,156],1.69,[304,160,333,1223,158,156,158,158,156],1.085,[304,163,333,325,158,156,158,158,156],[],[731],[],[],[1230],"KITTI odometry, trained on 00-06 (marked *) and tested on 07-10; trel = average translational RMSE (%) over 100-800 m subsequences; rows other than LOAM w\u002Fo mapping and Ours are copied from LO-Net [10]; LOAM is a full system with mapping, others are odometry only",[1232,1239,1245,1252,1259,1264,1273,1279,1286,1293,1300,1305,1311,1317,1326,1333,1339,1344,1350,1356,1362,1369,1374,1381,1387,1394,1400,1406,1410,1416,1422,1428,1433,1439,1444,1448,1454],{"group":1233,"slug":1234,"sourceLabel":1235,"table":1236,"selfRows":349,"datasets":1237},"censi2008_plicp:Fig. 3 table","censi2008-plicp-fig-3-table","Censi, 2008","Fig. 3 table",[1238],"Minguez et al. (2006) wheelchair SICK log (778 scans)",{"group":1240,"slug":1241,"sourceLabel":1242,"table":451,"selfRows":349,"datasets":1243},"pang2018ndticp:Table II","pang2018ndticp-table-ii","Pang et al., 2018",[1244],"MCity test route (350 m)",{"group":1246,"slug":1247,"sourceLabel":1248,"table":1249,"selfRows":349,"datasets":1250},"rusinkiewicz2019symmetric:Fig. 5","rusinkiewicz2019symmetric-fig-5","Rusinkiewicz, 2019","Fig. 5",[1251],"bunny range scans (Turk and Levoy 1994)",{"group":1253,"slug":1254,"sourceLabel":1255,"table":1256,"selfRows":318,"datasets":1257},"razlaw2015evaluation:Table III","razlaw2015evaluation-table-iii","Razlaw et al., 2015","Table III",[1258],"Razlaw et al. MAV laser datasets",{"group":1260,"slug":1261,"sourceLabel":1242,"table":1262,"selfRows":287,"datasets":1263},"pang2018ndticp:Table I","pang2018ndticp-table-i","Table I",[1244],{"group":1265,"slug":1266,"sourceLabel":1267,"table":451,"selfRows":271,"datasets":1268},"balm2_2023:Table II","balm2-2023-table-ii","Liu et al., 2023a",[1269,1270,1271,1272],"Hilti 2021, VIRAL and UrbanLoco (19 sequences)","Hilti SLAM Challenge 2021","NTU VIRAL","UrbanLoco",{"group":1274,"slug":1275,"sourceLabel":1276,"table":87,"selfRows":255,"datasets":1277},"lim2024quatropp:Table 6","lim2024quatropp-table-6","Lim et al., 2024",[1278],"KITTI",{"group":1280,"slug":1281,"sourceLabel":1282,"table":1283,"selfRows":255,"datasets":1284},"zhang2024globalbimreg:Table 2","zhang2024globalbimreg-table-2","Zhang et al., 2024b","Table 2",[1285],"ISPRS benchmark on indoor modelling",{"group":1287,"slug":1288,"sourceLabel":1289,"table":1290,"selfRows":255,"datasets":1291},"zhou2016fgr:Table 3","zhou2016fgr-table-3","Zhou et al., 2016","Table 3",[1292],"Synthetic range images",{"group":1294,"slug":1295,"sourceLabel":1296,"table":1290,"selfRows":221,"datasets":1297},"nerfloam2023:Table 3","nerfloam2023-table-3","Deng et al., 2023",[740,1298,1299],"MaiCity","Newer College",{"group":1301,"slug":1302,"sourceLabel":1296,"table":1303,"selfRows":221,"datasets":1304},"nerfloam2023:Table 5","nerfloam2023-table-5","Table 5",[740],{"group":1306,"slug":1307,"sourceLabel":6,"table":1308,"selfRows":166,"datasets":1309},"besl1992icp:Text Sec.VI-C2","besl1992icp-text-sec-vi-c2","Text Sec.VI-C2",[1310],"NRCC African mask range data (Hyscan sensor)",{"group":1312,"slug":1313,"sourceLabel":1314,"table":451,"selfRows":166,"datasets":1315},"koide2021vgicp:Table II","koide2021vgicp-table-ii","Koide et al., 2021b",[1316],"authors' HDL-32e sequences",{"group":1318,"slug":1319,"sourceLabel":1320,"table":1321,"selfRows":166,"datasets":1322},"magnusson2007ndt3d:Text Sec. 5.2.1","magnusson2007ndt3d-text-sec-5-2-1","Magnusson et al., 2007","Text Sec. 5.2.1",[1323,1324,1325],"JUNCTION","JUNCTION and TUNNEL","TUNNEL",{"group":1327,"slug":1328,"sourceLabel":1329,"table":1330,"selfRows":166,"datasets":1331},"magnusson2009thesis:Text Sec. 6.4.2 (Figs. 6.20-6.21 captions)","magnusson2009thesis-text-sec-6-4-2-figs-6-20-6-21-captions","Magnusson, 2009","Text Sec. 6.4.2 (Figs. 6.20-6.21 captions)",[1332],"Kvarntorp tunnel scan pair (collaborative comparison)",{"group":1334,"slug":1335,"sourceLabel":1242,"table":1336,"selfRows":166,"datasets":1337},"pang2018ndticp:Text Sec. IV-E","pang2018ndticp-text-sec-iv-e","Text Sec. IV-E",[1338],"MCity route (1 km)",{"group":1340,"slug":1341,"sourceLabel":86,"table":1342,"selfRows":166,"datasets":1343},"pomerleau2013comparing:Text Sec. 5.2.4","pomerleau2013comparing-text-sec-5-2-4","Text Sec. 5.2.4",[105],{"group":1345,"slug":1346,"sourceLabel":6,"table":1347,"selfRows":163,"datasets":1348},"besl1992icp:Text Sec.VI-A","besl1992icp-text-sec-vi-a","Text Sec.VI-A",[1349],"Table I point sets (synthetic)",{"group":1351,"slug":1352,"sourceLabel":6,"table":1353,"selfRows":163,"datasets":1354},"besl1992icp:Text Sec.VI-C1","besl1992icp-text-sec-vi-c1","Text Sec.VI-C1",[1355],"synthetic Bezier surface patch",{"group":1357,"slug":1358,"sourceLabel":1235,"table":1359,"selfRows":163,"datasets":1360},"censi2008_plicp:Text Sec. V.B table","censi2008-plicp-text-sec-v-b-table","Text Sec. V.B table",[1361],"Minguez et al. (2006) wheelchair SICK log",{"group":1363,"slug":1364,"sourceLabel":1365,"table":1366,"selfRows":163,"datasets":1367},"genzicp2025:Table VI","genzicp2025-table-vi","Lee et al., 2025a","Table VI",[1368],"SubT-MRS",{"group":1370,"slug":1371,"sourceLabel":1314,"table":1262,"selfRows":163,"datasets":1372},"koide2021vgicp:Table I","koide2021vgicp-table-i",[1373],"authors' simulated LiDAR sequence",{"group":1375,"slug":1376,"sourceLabel":1377,"table":1378,"selfRows":163,"datasets":1379},"magnusson2009icpndt:Text Fig. 7 caption","magnusson2009icpndt-text-fig-7-caption","Magnusson et al., 2009","Text Fig. 7 caption",[1380],"Kvarntorp data set A",{"group":1382,"slug":1383,"sourceLabel":1329,"table":1384,"selfRows":163,"datasets":1385},"magnusson2009thesis:Text Sec. 6.4.2 (Crossing)","magnusson2009thesis-text-sec-6-4-2-crossing","Text Sec. 6.4.2 (Crossing)",[1386],"Crossing (Kvarntorp-Loop scans 36 and 38)",{"group":1388,"slug":1389,"sourceLabel":1329,"table":1390,"selfRows":163,"datasets":1391},"magnusson2009thesis:Text Sec. 6.4.3 (Figs. 6.27-6.28 captions)","magnusson2009thesis-text-sec-6-4-3-figs-6-27-6-28-captions","Text Sec. 6.4.3 (Figs. 6.27-6.28 captions)",[1392,1393],"Kvarntorp-Loop (Tjorven, 48 scans)","Mission-4 (Kurt3D, 55 scans, closed loop)",{"group":1395,"slug":1396,"sourceLabel":1242,"table":1397,"selfRows":163,"datasets":1398},"pang2018ndticp:Table IV","pang2018ndticp-table-iv","Table IV",[1399],"MSU West Circle Drive",{"group":1401,"slug":1402,"sourceLabel":1242,"table":1403,"selfRows":163,"datasets":1404},"pang2018ndticp:Text Sec. IV-F","pang2018ndticp-text-sec-iv-f","Text Sec. IV-F",[1405],"MCity",{"group":1407,"slug":1408,"sourceLabel":1267,"table":1256,"selfRows":160,"datasets":1409},"balm2_2023:Table III","balm2-2023-table-iii",[1270],{"group":1411,"slug":1412,"sourceLabel":6,"table":1413,"selfRows":160,"datasets":1414},"besl1992icp:Text Sec.VI-A1","besl1992icp-text-sec-vi-a1","Text Sec.VI-A1",[1415],"NRCC African mask range data",{"group":1417,"slug":1418,"sourceLabel":6,"table":1419,"selfRows":160,"datasets":1420},"besl1992icp:Text Sec.VI-C3","besl1992icp-text-sec-vi-c3","Text Sec.VI-C3",[1421],"University of Arizona terrain data",{"group":1423,"slug":1424,"sourceLabel":1320,"table":1425,"selfRows":160,"datasets":1426},"magnusson2007ndt3d:Text Sec. 5.2.2","magnusson2007ndt3d-text-sec-5-2-2","Text Sec. 5.2.2",[1427],"KVARNTORP-LOOP",{"group":1429,"slug":1430,"sourceLabel":1377,"table":1431,"selfRows":160,"datasets":1432},"magnusson2009icpndt:Text Fig. 8 caption","magnusson2009icpndt-text-fig-8-caption","Text Fig. 8 caption",[1380],{"group":1434,"slug":1435,"sourceLabel":1377,"table":1436,"selfRows":160,"datasets":1437},"magnusson2009icpndt:Text Sec. IV-D-2","magnusson2009icpndt-text-sec-iv-d-2","Text Sec. IV-D-2",[1438],"Kvarntorp data set B",{"group":1440,"slug":1441,"sourceLabel":1377,"table":1442,"selfRows":160,"datasets":1443},"magnusson2009icpndt:Text Sec. IV-D-3","magnusson2009icpndt-text-sec-iv-d-3","Text Sec. IV-D-3",[1438],{"group":1445,"slug":1446,"sourceLabel":1242,"table":1436,"selfRows":160,"datasets":1447},"pang2018ndticp:Text Sec. IV-D-2","pang2018ndticp-text-sec-iv-d-2",[1399],{"group":1449,"slug":1450,"sourceLabel":1451,"table":1452,"selfRows":160,"datasets":1453},"zhang2024_3dlidarslam_survey:Table 8","zhang2024-3dlidarslam-survey-table-8","Zhang et al., 2024a","Table 8",[740],{"group":1455,"slug":1456,"sourceLabel":1451,"table":1457,"selfRows":160,"datasets":1458},"zhang2024_3dlidarslam_survey:Table 9","zhang2024-3dlidarslam-survey-table-9","Table 9",[740],1790510665066]