[{"data":1,"prerenderedAt":930},["ShallowReactive",2],{"method-elasticfusion2015":3},{"method":4,"reference":55,"equipment":77,"figures":101,"results":102},{"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":28,"sensors":32,"platform":34,"estimator":36,"association":37,"timeModel":38,"deskew":39,"loopClosure":40,"globalOptimization":41,"mapRepresentation":42,"prior":43,"outputGeometry":44,"compute":45,"codeUrl":46,"codeLicense":47,"relatedVersions":48},"elasticfusion2015","Whelan et al., 2015a","ElasticFusion","ElasticFusion: Dense SLAM Without A Pose Graph",2015,"classic","C08","full_slam_with_global_correction","ElasticFusion 以面元（surfel）表示稠密地圖，採用由目前影像對模型（frame-to-model）的稠密追蹤與時間視窗內的面元融合。系統盡量頻繁地做局部模型對模型迴圈閉合，並以隨機蕨（randomised fern）影像編碼偵測全域迴圈，再以非剛性變形直接校正地圖，而不使用位姿圖或事後處理。作者將適用範圍定為房間尺度。","ElasticFusion maintains a surfel map with dense frame-to-model tracking and applies frequent local and fern-based global loop closures as non-rigid map deformations instead of pose-graph optimisation, at room scale.","full_text_reviewed","peer_reviewed_published","main_body","論文未報告營建測試；表面精度評估使用 ICL-NUIM 合成資料。房間尺度與 GPU 需求限制其直接用於整層或整棟建築（推論）。",[20,21,22],"simulation","public_benchmark","independent_reference",[24,25,26,27],"Globally consistent room-scale surfel maps online without pose graph or post-processing (abstract)","Frequent non-rigid deformations improved both trajectory and surface reconstruction in authors' evaluation (conclusion; Tables I to III)","Lowest surface reconstruction error on all four ICL-NUIM living-room sequences (Table III)","Frame-to-model tracking alone is already comparable to pose-graph systems on TUM RGB-D (Sec. VII-A)",[29,30,31],"Designed and evaluated for room-scale environments; scalability beyond whole rooms left to future work (conclusion)","Relies on GPU programming for tracking, prediction and map management (Sec. II)","Frame processing time grows with the number of surfels in the map (Sec. VII-C; Fig. 6)",[33],"RGB-D",[35],"handheld","Gauss-Newton on E_track = E_icp + 0.1 E_rgb over a three-level coarse-to-fine pyramid (6x6 normal equations via CUDA tree reduction, Cholesky on CPU); loop closures applied through an embedded deformation graph rebuilt each frame by systematic sampling of surfels, nodes connected by initialisation time (k = 4), optimised by Gauss-Newton with sparse Cholesky on the CPU using rotation, regularisation, constraint and pin terms (weights 1, 10, 100, 100)","frame-to-model: point-to-plane ICP with projective data association between the live depth map and the splatted active-model depth prediction, plus photometric intensity error between the live colour image and the splatted model colour prediction (weight 0.1); the same registration is used for model-to-model loop alignment","discrete poses; surfels carry timestamps for time-windowed fusion (abstract)","not_reported","local: each frame the active model prediction is registered to the inactive model prediction and accepted if residual, inlier count and covariance eigenvalue checks pass, then the map is deformed and the region reactivated; global: randomised fern database of predicted views at 80x60, matched views registered and accepted only if the resulting deformation is consistent with the map geometry; the fern database can also serve relocalisation, not needed in the evaluated data","non-rigid deformation of the surfel map instead of pose-graph optimisation (abstract; conclusion)","unordered list of surfels (position, normal, colour, weight, radius, initialisation and last-update timestamps) split into active and inactive sets by a time window; up to 4.8 million surfels in the qualitative scans","none","surfel map (oriented points with radius and colour)","desktop PC with Intel Core i7-4930K 3.4 GHz, 32 GB RAM and nVidia GeForce GTX 780 Ti with 3 GB; CUDA for tracking reduction and OpenGL shading language for prediction and map management; frame time rises with surfel count, overall average 31 ms and peak average 45 ms (worst case 22 Hz) on the Hotel sequence","https:\u002F\u002Fgithub.com\u002Fmp3guy\u002FElasticFusion","custom licence, non-commercial, internal or academic research purposes only (LICENSE.txt)",[49,53],{"relation":50,"title":51,"doi_or_url":52},"journal_extension","ElasticFusion: Real-time dense SLAM and light source estimation (IJRR 35(14):1697-1716, online 2016-09-30)","10.1177\u002F0278364916669237",{"relation":54,"title":7,"doi_or_url":46},"code_release",{"id":5,"kind":56,"shortName":7,"title":8,"authors":57,"year":9,"venue":63,"venueType":64,"publisher":65,"volumeIssuePages":39,"doi":66,"arxivId":67,"url":68,"firstPublicDate":69,"publicationStatus":16,"metadataStatus":70,"fulltextStatus":15,"era":10,"classicReason":71,"codeUrl":46,"cluster":11,"topics":72,"mdpi":73,"verification":74,"label":6,"fulltextRoute":75,"versionRead":76,"addedByCensus":73},"method",[58,59,60,61,62],"Thomas Whelan","Stefan Leutenegger","Renato Salas Moreno","Ben Glocker","Andrew Davison","Robotics: Science and Systems XI","conference","RSS Foundation","10.15607\u002Frss.2015.xi.001",null,"https:\u002F\u002Fwww.roboticsproceedings.org\u002Frss11\u002Fp01.pdf","2015-07-13","metadata_verified","principle reused: surfel-based dense map with frequent non-rigid deformation replacing pose-graph optimisation; standard dense RGB-D baseline.",[11],false,"confirmed","publisher OA","RSS XI (2015) proceedings PDF, version of record, DOI 10.15607\u002FRSS.2015.XI.001 (9 pages); IJRR 2016 extension not read",[78,85,92,98],{"category":79,"model":80,"canonical":80,"role":81,"dataset":82,"specs":83,"locator":84},"rgbd","standard RGB-D camera (Microsoft Kinect or ASUS Xtion Pro Live named as examples)","method input","ElasticFusion qualitative datasets (Copy from Zhou and Koltun, Lab, Hotel, Office)","device used for the authors' hand-held qualitative datasets not stated","Sec. II footnote 1; Sec. VII-B",{"category":86,"model":87,"canonical":87,"role":88,"dataset":89,"specs":90,"locator":91},"other","highly precise motion capture system","reference or ground truth","TUM RGB-D","synchronised ground-truth poses of the TUM RGB-D benchmark","Sec. VII-A",{"category":93,"model":94,"canonical":94,"role":95,"dataset":67,"specs":96,"locator":97},"compute","Intel Core i7-4930K","compute for runtime","3.4GHz, 32GB of RAM","Sec. VII-C",{"category":93,"model":99,"canonical":99,"role":95,"dataset":67,"specs":100,"locator":97},"nVidia GeForce GTX 780 Ti","3GB of memory",[],{"totalRows":103,"groupCount":104,"groups":105,"others":762},221,36,[106,332,584,654],{"slug":107,"group":108,"sourceId":109,"sourceLabel":110,"table":111,"selfRows":112,"metrics":113,"seqs":124,"entrants":135,"cells":152,"outcomes":325,"locators":326,"hardware":328,"wordings":329,"notes":330},"surfelmeshing2020-table-2-ground-truth-trajectories","surfelmeshing2020:Table 2 (ground-truth trajectories)","surfelmeshing2020","Schöps et al., 2020","Table 2 (ground-truth trajectories)",24,[114,118,120],{"label":115,"unit":116,"statistic":39,"alignment":117},"Accuracy [%] (share of reconstructed surfels within 1 cm of ground truth)","%","SE3",{"label":119,"unit":116,"statistic":39,"alignment":117},"Completeness [%] (share of ground-truth points within 1 cm of the reconstruction)",{"label":121,"unit":122,"statistic":123,"alignment":117},"Curvature [0.01\u002Fm] (mean curvature, smoothness)","0.01 1\u002Fm","mean",[125,129,131,133],{"dataset":126,"sequence":127,"environment":128},"ICL-NUIM","kt0","synthetic indoor living room",{"dataset":126,"sequence":130,"environment":128},"kt1",{"dataset":126,"sequence":132,"environment":128},"kt2",{"dataset":126,"sequence":134,"environment":128},"kt3",[136,140,142,144,146,148,150],{"name":137,"methodId":138,"linkable":139,"proposed":73,"self":73},"InfiniTAM [29]","infinitam2015",true,{"name":141,"methodId":138,"linkable":139,"proposed":73,"self":73},"InfiniTAM [29] - smoothed",{"name":143,"methodId":67,"linkable":73,"proposed":73,"self":73},"FastFusion [27]",{"name":145,"methodId":67,"linkable":73,"proposed":73,"self":73},"FastFusion [27] - smoothed",{"name":147,"methodId":5,"linkable":139,"proposed":73,"self":139},"ElasticFusion [17]",{"name":149,"methodId":5,"linkable":139,"proposed":73,"self":139},"ElasticFusion [17] - smoothed",{"name":151,"methodId":109,"linkable":139,"proposed":139,"self":73},"SurfelMeshing (Ours)",[153,157,160,163,166,169,172,175,177,179,181,183,185,187,189,191,193,195,197,199,201,203,205,207,209,211,213,215,217,219,221,223,225,227,229,230,232,234,236,238,240,242,244,246,248,250,251,253,255,257,259,261,263,264,266,268,270,272,274,276,278,280,282,284,286,288,290,292,294,296,298,300,302,304,306,308,310,311,313,315,317,319,321,323],[154,154,154,155,156,154,156,156,154],0,76.4,-1,[158,154,154,159,156,154,156,156,154],1,78.3,[161,154,154,162,156,154,156,156,154],2,85.5,[164,154,154,165,156,154,156,156,154],3,75.9,[167,154,154,168,156,154,156,156,154],4,96.2,[170,154,154,171,156,154,156,156,154],5,95.7,[173,154,154,174,156,154,156,156,154],6,93.5,[154,154,158,176,156,154,156,156,154],68.4,[158,154,158,178,156,154,156,156,154],68.3,[161,154,158,180,156,154,156,156,154],80.1,[164,154,158,182,156,154,156,156,154],78.8,[167,154,158,184,156,154,156,156,154],83.1,[170,154,158,186,156,154,156,156,154],82.1,[173,154,158,188,156,154,156,156,154],86.4,[154,154,161,190,156,154,156,156,154],56.6,[158,154,161,192,156,154,156,156,154],58.1,[161,154,161,194,156,154,156,156,154],64.2,[164,154,161,196,156,154,156,156,154],52.6,[167,154,161,198,156,154,156,156,154],97.1,[170,154,161,200,156,154,156,156,154],96.6,[173,154,161,202,156,154,156,156,154],69.5,[154,154,164,204,156,154,156,156,154],54.4,[158,154,164,206,156,154,156,156,154],58.3,[161,154,164,208,156,154,156,156,154],85.3,[164,154,164,210,156,154,156,156,154],72.5,[167,154,164,212,156,154,156,156,154],93.7,[170,154,164,214,156,154,156,156,154],92.2,[173,154,164,216,156,154,156,156,154],74,[154,158,154,218,156,154,156,156,154],53.5,[158,158,154,220,156,154,156,156,154],51.6,[161,158,154,222,156,154,156,156,154],54.7,[164,158,154,224,156,154,156,156,154],45.6,[167,158,154,226,156,154,156,156,154],38.8,[170,158,154,228,156,154,156,156,154],38.9,[173,158,154,224,156,154,156,156,154],[154,158,158,231,156,154,156,156,154],66.5,[158,158,158,233,156,154,156,156,154],62.8,[161,158,158,235,156,154,156,156,154],67.3,[164,158,158,237,156,154,156,156,154],63,[167,158,158,239,156,154,156,156,154],46,[170,158,158,241,156,154,156,156,154],45.3,[173,158,158,243,156,154,156,156,154],58.6,[154,158,161,245,156,154,156,156,154],46.7,[158,158,161,247,156,154,156,156,154],42.6,[161,158,161,249,156,154,156,156,154],48.4,[164,158,161,226,156,154,156,156,154],[167,158,161,252,156,154,156,156,154],22.8,[170,158,161,254,156,154,156,156,154],23.1,[173,158,161,256,156,154,156,156,154],30.8,[154,158,164,258,156,154,156,156,154],61.6,[158,158,164,260,156,154,156,156,154],59.9,[161,158,164,262,156,154,156,156,154],82.8,[164,158,164,231,156,154,156,156,154],[167,158,164,265,156,154,156,156,154],40,[170,158,164,267,156,154,156,156,154],40.4,[173,158,164,269,156,154,156,156,154],52.1,[154,161,154,271,156,154,156,156,154],2.48,[158,161,154,273,156,154,156,156,154],1.46,[161,161,154,275,156,154,156,156,154],0.99,[164,161,154,277,156,154,156,156,154],0.63,[167,161,154,279,156,154,156,156,154],0.24,[170,161,154,281,156,154,156,156,154],0.18,[173,161,154,283,156,154,156,156,154],0.15,[154,161,158,285,156,154,156,156,154],2.23,[158,161,158,287,156,154,156,156,154],0.93,[161,161,158,289,156,154,156,156,154],1.47,[164,161,158,291,156,154,156,156,154],0.87,[167,161,158,293,156,154,156,156,154],0.43,[170,161,158,295,156,154,156,156,154],0.35,[173,161,158,297,156,154,156,156,154],0.17,[154,161,161,299,156,154,156,156,154],4.71,[158,161,161,301,156,154,156,156,154],1.71,[161,161,161,303,156,154,156,156,154],1.68,[164,161,161,305,156,154,156,156,154],1.2,[167,161,161,307,156,154,156,156,154],0.34,[170,161,161,309,156,154,156,156,154],0.28,[173,161,161,281,156,154,156,156,154],[154,161,164,312,156,154,156,156,154],3.69,[158,161,164,314,156,154,156,156,154],1.34,[161,161,164,316,156,154,156,156,154],1.33,[164,161,164,318,156,154,156,156,154],0.92,[167,161,164,320,156,154,156,156,154],0.47,[170,161,164,322,156,154,156,156,154],0.41,[173,161,164,324,156,154,156,156,154],0.32,[],[327],"Table 2",[],[],[331],"ICL-NUIM living room with simulated depth noise; ground-truth trajectories used and loop-closure handling disabled for all methods; reconstructions aligned to the ground-truth model with point-to-plane ICP; evaluation threshold 1 cm; 'smoothed' = same bilateral filter as SurfelMeshing preprocessing",{"slug":333,"group":334,"sourceId":335,"sourceLabel":336,"table":337,"selfRows":338,"metrics":339,"seqs":347,"entrants":372,"cells":383,"outcomes":577,"locators":579,"hardware":580,"wordings":581,"notes":582},"staticfusion2018-table-i","staticfusion2018:Table I","staticfusion2018","Scona et al., 2018","Table I",22,[340,344],{"label":341,"unit":342,"statistic":343,"alignment":39},"Trans. RPE RMSE (cm\u002Fs)","cm\u002Fs","RMSE",{"label":345,"unit":346,"statistic":343,"alignment":39},"Rot. RPE RMSE (deg\u002Fs)","deg\u002Fs",[348,352,354,356,358,360,362,364,366,368,370],{"dataset":349,"sequence":350,"environment":351},"TUM RGB-D (Freiburg)","fr1\u002Fxyz","indoor office scenes, static to highly dynamic (walking people), RGB-D camera (carrying mode not stated in the paper)",{"dataset":349,"sequence":353,"environment":351},"fr1\u002Fdesk",{"dataset":349,"sequence":355,"environment":351},"fr1\u002Fdesk2",{"dataset":349,"sequence":357,"environment":351},"fr1\u002Fplant",{"dataset":349,"sequence":359,"environment":351},"fr3\u002Fsit_static",{"dataset":349,"sequence":361,"environment":351},"fr3\u002Fsit_xyz",{"dataset":349,"sequence":363,"environment":351},"fr3\u002Fsit_halfsphere",{"dataset":349,"sequence":365,"environment":351},"fr3\u002Fwalk_static",{"dataset":349,"sequence":367,"environment":351},"fr3\u002Fwalk_xyz",{"dataset":349,"sequence":369,"environment":351},"fr3\u002Fwalk_halfsphere*",{"dataset":349,"sequence":371,"environment":351},"fr3\u002Fwalk_halfsphere",[373,375,377,379,381],{"name":374,"methodId":67,"linkable":73,"proposed":73,"self":73},"VO-SF (Jaimez et al. joint visual odometry and scene flow)",{"name":376,"methodId":5,"linkable":139,"proposed":73,"self":139},"EF (ElasticFusion)",{"name":378,"methodId":67,"linkable":73,"proposed":73,"self":73},"CF (Co-Fusion)",{"name":380,"methodId":67,"linkable":73,"proposed":73,"self":73},"BaMVO (Kim et al.)",{"name":382,"methodId":335,"linkable":139,"proposed":139,"self":73},"SF (StaticFusion)",[384,386,388,390,391,392,394,396,398,399,400,402,404,406,407,408,410,411,413,414,416,418,420,422,423,424,426,428,430,432,434,436,438,439,441,442,445,447,449,451,453,456,457,459,461,463,465,467,469,470,471,474,476,477,479,481,482,484,485,486,488,490,492,494,495,497,499,501,503,504,506,507,509,511,512,514,516,518,520,522,523,525,527,528,530,531,533,535,537,539,541,542,544,546,548,550,552,553,555,557,559,561,562,564,565,567,569,571,573,575],[154,154,154,385,156,154,156,156,154],2.1,[158,154,154,387,156,154,156,156,154],1.9,[161,154,154,389,156,154,156,156,154],2.3,[164,154,154,67,154,154,156,156,154],[167,154,154,389,156,154,156,156,154],[154,154,158,393,156,154,156,156,154],3.7,[158,154,158,395,156,154,156,156,154],2.9,[161,154,158,397,156,154,156,156,154],9,[164,154,158,67,154,154,156,156,154],[167,154,158,164,156,154,156,156,154],[154,154,161,401,156,154,156,156,154],5.4,[158,154,161,403,156,154,156,156,154],7.2,[161,154,161,405,156,154,156,156,154],9.2,[164,154,161,67,154,154,156,156,154],[167,154,161,170,156,154,156,156,154],[154,154,164,409,156,154,156,156,154],6.1,[158,154,164,170,156,154,156,156,154],[161,154,164,412,156,154,156,156,154],8.9,[164,154,164,67,154,154,156,156,154],[167,154,164,415,156,154,156,156,154],10.4,[154,154,167,417,156,154,156,156,154],2.4,[158,154,167,419,156,154,156,156,154],0.9,[161,154,167,421,156,154,156,156,154],1.1,[164,154,167,417,156,154,156,156,154],[167,154,167,421,156,154,156,156,154],[154,154,170,425,156,154,156,156,154],5.7,[158,154,170,427,156,154,156,156,154],1.6,[161,154,170,429,156,154,156,156,154],2.7,[164,154,170,431,156,154,156,156,154],4.8,[167,154,170,433,156,154,156,156,154],2.8,[154,154,173,435,156,154,156,156,154],7.5,[158,154,173,437,156,154,156,156,154],17.2,[161,154,173,164,156,154,156,156,154],[164,154,173,440,156,154,156,156,154],5.8,[167,154,173,164,156,154,156,156,154],[154,154,443,444,156,154,156,156,154],7,10.1,[158,154,443,446,156,154,156,156,154],26,[161,154,443,448,156,154,156,156,154],22.4,[164,154,443,450,156,154,156,156,154],13.3,[167,154,443,452,156,154,156,156,154],1.3,[154,154,454,455,156,154,156,156,154],8,27.7,[158,154,454,112,156,154,156,156,154],[161,154,454,458,156,154,156,156,154],32.9,[164,154,454,460,156,154,156,156,154],23.2,[167,154,454,462,156,154,156,156,154],12.1,[154,154,397,464,156,154,156,156,154],24.8,[158,154,397,466,156,154,156,156,154],16.3,[161,154,397,468,156,154,156,156,154],31.1,[164,154,397,67,154,154,156,156,154],[167,154,397,170,156,154,156,156,154],[154,154,472,473,156,154,156,156,154],10,33.5,[158,154,472,475,156,154,156,156,154],20.5,[161,154,472,265,156,154,156,156,154],[164,154,472,478,156,154,156,156,154],17.3,[167,154,472,480,156,154,156,156,154],20.7,[154,158,154,158,156,154,156,156,154],[158,158,154,483,156,154,156,156,154],0.91,[161,158,154,314,156,154,156,156,154],[164,158,154,67,154,154,156,156,154],[167,158,154,487,156,154,156,156,154],1.42,[154,158,158,489,156,154,156,156,154],1.77,[158,158,158,491,156,154,156,156,154],1.48,[161,158,158,493,156,154,156,156,154],4.49,[164,158,158,67,154,154,156,156,154],[167,158,158,496,156,154,156,156,154],2.17,[154,158,161,498,156,154,156,156,154],2.45,[158,158,161,500,156,154,156,156,154],4.07,[161,158,161,502,156,154,156,156,154],4.79,[164,158,161,67,154,154,156,156,154],[167,158,161,505,156,154,156,156,154],3.39,[154,158,164,161,156,154,156,156,154],[158,158,164,508,156,154,156,156,154],1.58,[161,158,164,510,156,154,156,156,154],3.02,[164,158,164,67,154,154,156,156,154],[167,158,164,513,156,154,156,156,154],3.16,[154,158,167,515,156,154,156,156,154],0.71,[158,158,167,517,156,154,156,156,154],0.3,[161,158,167,519,156,154,156,156,154],0.44,[164,158,167,521,156,154,156,156,154],0.69,[167,158,167,293,156,154,156,156,154],[154,158,170,524,156,154,156,156,154],1.44,[158,158,170,526,156,154,156,156,154],0.59,[161,158,170,158,156,154,156,156,154],[164,158,170,529,156,154,156,156,154],1.38,[167,158,170,318,156,154,156,156,154],[154,158,173,532,156,154,156,156,154],2.98,[158,158,173,534,156,154,156,156,154],4.56,[161,158,173,536,156,154,156,156,154],1.92,[164,158,173,538,156,154,156,156,154],2.88,[167,158,173,540,156,154,156,156,154],2.11,[154,158,443,303,156,154,156,156,154],[158,158,443,543,156,154,156,156,154],4.77,[161,158,443,545,156,154,156,156,154],4.01,[164,158,443,547,156,154,156,156,154],2.08,[167,158,443,549,156,154,156,156,154],0.38,[154,158,454,551,156,154,156,156,154],5.11,[158,158,454,502,156,154,156,156,154],[161,158,454,554,156,154,156,156,154],5.55,[164,158,454,556,156,154,156,156,154],4.39,[167,158,454,558,156,154,156,156,154],2.66,[154,158,397,560,156,154,156,156,154],5.49,[158,158,397,425,156,154,156,156,154],[161,158,397,563,156,154,156,156,154],8.45,[164,158,397,67,154,154,156,156,154],[167,158,397,566,156,154,156,156,154],2.18,[154,158,472,568,156,154,156,156,154],6.69,[158,158,472,570,156,154,156,156,154],6.41,[161,158,472,572,156,154,156,156,154],13.02,[164,158,472,574,156,154,156,156,154],4.28,[167,158,472,576,156,154,156,156,154],5.04,[578],"not reported (BaMVO shown only for sequences evaluated in its original publication)",[337],[],[],[583],"TUM (Freiburg) RGB-D sequences grouped as static (fr1), low dynamic (fr3\u002Fsit) and high dynamic (fr3\u002Fwalk) environments; StaticFusion and VO-SF at QVGA, ElasticFusion and Co-Fusion at their default VGA; fr3\u002Fwalk_halfsphere* skips the first 5 s of high dynamics; relative pose error per second",{"slug":585,"group":586,"sourceId":109,"sourceLabel":110,"table":587,"selfRows":588,"metrics":589,"seqs":593,"entrants":597,"cells":601,"outcomes":648,"locators":649,"hardware":650,"wordings":651,"notes":652},"surfelmeshing2020-table-2-loop-closure-trajectories","surfelmeshing2020:Table 2 (loop-closure trajectories)","Table 2 (loop-closure trajectories)",18,[590,591,592],{"label":115,"unit":116,"statistic":39,"alignment":117},{"label":119,"unit":116,"statistic":39,"alignment":117},{"label":121,"unit":122,"statistic":123,"alignment":117},[594,595,596],{"dataset":126,"sequence":127,"environment":128},{"dataset":126,"sequence":130,"environment":128},{"dataset":126,"sequence":132,"environment":128},[598,599,600],{"name":147,"methodId":5,"linkable":139,"proposed":73,"self":139},{"name":149,"methodId":5,"linkable":139,"proposed":73,"self":139},{"name":151,"methodId":109,"linkable":139,"proposed":139,"self":73},[602,604,606,608,610,612,614,616,618,620,622,624,626,628,630,631,632,633,635,637,639,641,643,644,645,646,647],[154,154,154,603,156,154,156,156,154],95.8,[158,154,154,605,156,154,156,156,154],96.8,[161,154,154,607,156,154,156,156,154],87.2,[154,154,158,609,156,154,156,156,154],64.9,[158,154,158,611,156,154,156,156,154],64.4,[161,154,158,613,156,154,156,156,154],58.5,[154,154,161,615,156,154,156,156,154],26.9,[158,154,161,617,156,154,156,156,154],26.8,[161,154,161,619,156,154,156,156,154],35,[154,158,154,621,156,154,156,156,154],40.6,[158,158,154,623,156,154,156,156,154],41.8,[161,158,154,625,156,154,156,156,154],44,[154,158,158,627,156,154,156,156,154],34.6,[158,158,158,629,156,154,156,156,154],34.5,[161,158,158,623,156,154,156,156,154],[154,158,161,440,156,154,156,156,154],[158,158,161,440,156,154,156,156,154],[161,158,161,634,156,154,156,156,154],15.9,[154,161,154,636,156,154,156,156,154],0.86,[158,161,154,638,156,154,156,156,154],0.37,[161,161,154,640,156,154,156,156,154],0.22,[154,161,158,642,156,154,156,156,154],0.39,[158,161,158,517,156,154,156,156,154],[161,161,158,283,156,154,156,156,154],[154,161,161,642,156,154,156,156,154],[158,161,161,295,156,154,156,156,154],[161,161,161,517,156,154,156,156,154],[],[327],[],[],[653],"ICL-NUIM living room with simulated depth noise; trajectories estimated with ElasticFusion including loop closures (kt3 omitted because ElasticFusion failed); aligned with point-to-plane ICP; threshold 1 cm; InfiniTAM and FastFusion cannot handle loop closures and have no values",{"slug":655,"group":656,"sourceId":335,"sourceLabel":336,"table":657,"selfRows":658,"metrics":659,"seqs":663,"entrants":675,"cells":680,"outcomes":756,"locators":757,"hardware":758,"wordings":759,"notes":760},"staticfusion2018-table-ii","staticfusion2018:Table II","Table II",11,[660],{"label":661,"unit":662,"statistic":343,"alignment":39},"Trans. ATE RMSE (cm)","cm",[664,665,666,667,668,669,670,671,672,673,674],{"dataset":349,"sequence":350,"environment":351},{"dataset":349,"sequence":353,"environment":351},{"dataset":349,"sequence":355,"environment":351},{"dataset":349,"sequence":357,"environment":351},{"dataset":349,"sequence":359,"environment":351},{"dataset":349,"sequence":361,"environment":351},{"dataset":349,"sequence":363,"environment":351},{"dataset":349,"sequence":365,"environment":351},{"dataset":349,"sequence":367,"environment":351},{"dataset":349,"sequence":369,"environment":351},{"dataset":349,"sequence":371,"environment":351},[676,677,678,679],{"name":374,"methodId":67,"linkable":73,"proposed":73,"self":73},{"name":376,"methodId":5,"linkable":139,"proposed":73,"self":139},{"name":378,"methodId":67,"linkable":73,"proposed":73,"self":73},{"name":382,"methodId":335,"linkable":139,"proposed":139,"self":73},[681,683,684,686,687,689,690,692,693,695,696,698,700,702,704,706,708,709,711,712,713,715,717,718,719,720,722,724,725,727,729,731,732,734,736,738,740,742,744,746,748,750,752,754],[154,154,154,682,156,154,156,156,154],5.1,[158,154,154,305,156,154,156,156,154],[161,154,154,685,156,154,156,156,154],1.4,[164,154,154,685,156,154,156,156,154],[154,154,158,688,156,154,156,156,154],5.6,[158,154,158,385,156,154,156,156,154],[161,154,158,691,156,154,156,156,154],17.7,[164,154,158,389,156,154,156,156,154],[154,154,161,694,156,154,156,156,154],17.4,[158,154,161,425,156,154,156,156,154],[161,154,161,697,156,154,156,156,154],16.8,[164,154,161,699,156,154,156,156,154],5.2,[154,154,164,701,156,154,156,156,154],7.8,[158,154,164,703,156,154,156,156,154],5.3,[161,154,164,705,156,154,156,156,154],12.6,[164,154,164,707,156,154,156,156,154],11.3,[154,154,167,395,156,154,156,156,154],[158,154,167,710,156,154,156,156,154],0.8,[161,154,167,421,156,154,156,156,154],[164,154,167,452,156,154,156,156,154],[154,154,170,714,156,154,156,156,154],11.1,[158,154,170,716,156,154,156,156,154],2.2,[161,154,170,429,156,154,156,156,154],[164,154,170,167,156,154,156,156,154],[154,154,173,588,156,154,156,156,154],[158,154,173,721,156,154,156,156,154],42.8,[161,154,173,723,156,154,156,156,154],3.6,[164,154,173,167,156,154,156,156,154],[154,154,443,726,156,154,156,156,154],32.7,[158,154,443,728,156,154,156,156,154],29.3,[161,154,443,730,156,154,156,156,154],55.1,[164,154,443,685,156,154,156,156,154],[154,154,454,733,156,154,156,156,154],87.4,[158,154,454,735,156,154,156,156,154],90.6,[161,154,454,737,156,154,156,156,154],69.6,[164,154,454,739,156,154,156,156,154],12.7,[154,154,397,741,156,154,156,156,154],48.2,[158,154,397,743,156,154,156,156,154],48.6,[161,154,397,745,156,154,156,156,154],75.6,[164,154,397,747,156,154,156,156,154],6.3,[154,154,472,749,156,154,156,156,154],73.9,[158,154,472,751,156,154,156,156,154],63.8,[161,154,472,753,156,154,156,156,154],80.3,[164,154,472,755,156,154,156,156,154],39.1,[],[657],[],[],[761],"TUM (Freiburg) RGB-D sequences grouped as static (fr1), low dynamic (fr3\u002Fsit) and high dynamic (fr3\u002Fwalk) environments; StaticFusion and VO-SF at QVGA, ElasticFusion and Co-Fusion at their default VGA; fr3\u002Fwalk_halfsphere* skips the first 5 s of high dynamics",[763,770,777,781,785,789,794,800,805,814,819,824,829,834,839,844,849,853,857,862,867,872,876,881,887,891,895,901,906,913,918,924],{"group":764,"slug":765,"sourceLabel":766,"table":767,"selfRows":397,"datasets":768},"yan2026_underground3dgsslam:Table III","yan2026-underground3dgsslam-table-iii","Yan et al., 2026b","Table III",[769],"Underground_RGB-D (authors' field test dataset)",{"group":771,"slug":772,"sourceLabel":773,"table":774,"selfRows":454,"datasets":775},"badslam2019:Table 3","badslam2019-table-3","Schöps et al., 2019","Table 3",[776],"synthetic TUM RGB-D renders (7 datasets per category)",{"group":778,"slug":779,"sourceLabel":6,"table":337,"selfRows":454,"datasets":780},"elasticfusion2015:Table I","elasticfusion2015-table-i",[89],{"group":782,"slug":783,"sourceLabel":6,"table":657,"selfRows":454,"datasets":784},"elasticfusion2015:Table II","elasticfusion2015-table-ii",[126],{"group":786,"slug":787,"sourceLabel":6,"table":767,"selfRows":454,"datasets":788},"elasticfusion2015:Table III","elasticfusion2015-table-iii",[126],{"group":790,"slug":791,"sourceLabel":792,"table":767,"selfRows":443,"datasets":793},"orbslam2_2017:Table III","orbslam2-2017-table-iii","Mur-Artal & Tardos, 2017",[89],{"group":795,"slug":796,"sourceLabel":797,"table":327,"selfRows":173,"datasets":798},"loopyslam2024:Table 2","loopyslam2024-table-2","Liso et al., 2024",[799],"TUM-RGBD",{"group":801,"slug":802,"sourceLabel":803,"table":774,"selfRows":173,"datasets":804},"pointslam2023:Table 3","pointslam2023-table-3","Sandström et al., 2023",[799],{"group":806,"slug":807,"sourceLabel":808,"table":809,"selfRows":173,"datasets":810},"splatam2024:Table 1","splatam2024-table-1","Keetha et al., 2024","Table 1",[811,812,813,799],"Replica","ScanNet (original)","ScanNet++",{"group":815,"slug":816,"sourceLabel":817,"table":337,"selfRows":170,"datasets":818},"cblox2018:Table I","cblox2018-table-i","Millane et al., 2018",[126],{"group":820,"slug":821,"sourceLabel":822,"table":774,"selfRows":167,"datasets":823},"bundlefusion2017:Table 3","bundlefusion2017-table-3","Dai et al., 2017a",[126],{"group":825,"slug":826,"sourceLabel":822,"table":827,"selfRows":167,"datasets":828},"bundlefusion2017:Table 4","bundlefusion2017-table-4","Table 4",[89],{"group":830,"slug":831,"sourceLabel":822,"table":832,"selfRows":167,"datasets":833},"bundlefusion2017:Table 6","bundlefusion2017-table-6","Table 6",[126],{"group":835,"slug":836,"sourceLabel":837,"table":337,"selfRows":167,"datasets":838},"densesurfelmapping2019:Table I","densesurfelmapping2019-table-i","Wang et al., 2019",[126],{"group":840,"slug":841,"sourceLabel":6,"table":842,"selfRows":167,"datasets":843},"elasticfusion2015:Text Sec. VII-B","elasticfusion2015-text-sec-vii-b","Text Sec. VII-B",[126],{"group":845,"slug":846,"sourceLabel":847,"table":337,"selfRows":167,"datasets":848},"flashfusion2018:Table I","flashfusion2018-table-i","Han & Fang, 2018",[89],{"group":850,"slug":851,"sourceLabel":847,"table":657,"selfRows":167,"datasets":852},"flashfusion2018:Table II","flashfusion2018-table-ii",[126],{"group":854,"slug":855,"sourceLabel":847,"table":767,"selfRows":167,"datasets":856},"flashfusion2018:Table III","flashfusion2018-table-iii",[126],{"group":858,"slug":859,"sourceLabel":860,"table":327,"selfRows":167,"datasets":861},"gsslam2024:Table 2","gsslam2024-table-2","Yan et al., 2024",[89],{"group":863,"slug":864,"sourceLabel":865,"table":767,"selfRows":167,"datasets":866},"manhattanslam2021:Table III","manhattanslam2021-table-iii","Yunus et al., 2021",[126],{"group":868,"slug":869,"sourceLabel":870,"table":327,"selfRows":167,"datasets":871},"psmslam2017:Table 2","psmslam2017-table-2","Yan et al., 2017",[89],{"group":873,"slug":874,"sourceLabel":870,"table":827,"selfRows":167,"datasets":875},"psmslam2017:Table 4","psmslam2017-table-4",[126],{"group":877,"slug":878,"sourceLabel":870,"table":879,"selfRows":167,"datasets":880},"psmslam2017:Table 5","psmslam2017-table-5","Table 5",[126],{"group":882,"slug":883,"sourceLabel":884,"table":885,"selfRows":167,"datasets":886},"rtgslam2024:Supp. Table 11","rtgslam2024-supp-table-11","Peng et al., 2024","Supp. Table 11",[811],{"group":888,"slug":889,"sourceLabel":884,"table":327,"selfRows":167,"datasets":890},"rtgslam2024:Table 2","rtgslam2024-table-2",[89],{"group":892,"slug":893,"sourceLabel":773,"table":327,"selfRows":164,"datasets":894},"badslam2019:Table 2","badslam2019-table-2",[89],{"group":896,"slug":897,"sourceLabel":6,"table":898,"selfRows":164,"datasets":899},"elasticfusion2015:Text Sec. VII-C","elasticfusion2015-text-sec-vii-c","Text Sec. VII-C",[900],"ElasticFusion qualitative datasets",{"group":902,"slug":903,"sourceLabel":766,"table":904,"selfRows":164,"datasets":905},"yan2026_underground3dgsslam:Table VI","yan2026-underground3dgsslam-table-vi","Table VI",[89],{"group":907,"slug":908,"sourceLabel":909,"table":910,"selfRows":161,"datasets":911},"droidslam2021:Fig. 4 table","droidslam2021-fig-4-table","Teed & Deng, 2021","Fig. 4 table",[912],"ETH3D SLAM benchmark",{"group":914,"slug":915,"sourceLabel":6,"table":916,"selfRows":161,"datasets":917},"elasticfusion2015:Text Sec. VII-A","elasticfusion2015-text-sec-vii-a","Text Sec. VII-A",[89],{"group":919,"slug":920,"sourceLabel":921,"table":327,"selfRows":158,"datasets":922},"ghadimzadeh2025slamnde:Table 2","ghadimzadeh2025slamnde-table-2","Ghadimzadeh Alamdari et al., 2025",[923],"Luleå SubT tunnel dataset (Koval et al. 2022)",{"group":925,"slug":926,"sourceLabel":336,"table":927,"selfRows":158,"datasets":928},"staticfusion2018:Text Sec.VII-B","staticfusion2018-text-sec-vii-b","Text Sec.VII-B",[929],"authors' hand-held selfie sequence",1790510656041]