[{"data":1,"prerenderedAt":828},["ShallowReactive",2],{"method-staticfusion2018":3},{"method":4,"reference":53,"equipment":77,"figures":90,"results":91},{"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":27,"sensors":33,"platform":35,"estimator":38,"association":39,"timeModel":40,"deskew":41,"loopClosure":42,"globalOptimization":42,"mapRepresentation":43,"prior":44,"outputGeometry":45,"compute":46,"codeUrl":47,"codeLicense":48,"relatedVersions":49},"staticfusion2018","Scona et al., 2018","StaticFusion","StaticFusion: Background Reconstruction for Dense RGB-D SLAM in Dynamic Environments",2018,"recent","C08","odometry_with_local_mapping","StaticFusion 是針對動態環境的 RGB-D 稠密 SLAM，同時估計相機運動與影像中哪些區域靜止。每張影像先以 K-means 依三維座標分成幾何群集，再與由靜態面元地圖渲染出的預測影像做光度與幾何直接對齊；每個群集有一個 0 至 1 的靜態分數，用來加權其殘差，分數則由殘差門檻、相鄰群集平滑與深度差先驗共同決定，並以 IRLS 交替求解位姿與分數。融合時只寫入靜態部分，每個面元以對數勝算累積被靜態點重複觀測的可信度，持續被動態點匹配的面元會被移除，因此地圖只保留背景結構，並把這個背景作為下一影格分割所需的時間資訊。","Dense RGB-D SLAM for dynamic scenes that jointly estimates camera motion and per-cluster static scores by score-weighted photometric and geometric alignment against a rendered static surfel map, and fuses only static data with per-surfel viability so the map keeps only the background.","full_text_reviewed","peer_reviewed_published","main_body","論文未在施工現場測試，評估為 TUM (Freiburg) 室內序列與兩段手持錄製的室內序列（人員與物件移動、自拍式移動）。只把靜態背景融入地圖並持續移除被動態點匹配的面元，對有人員走動的施工中室內掃描有參考價值；但作者指出初始 1 至 2 秒若動態元素超過約 20% 至 30% 便可能失敗，因此工地掃描起始時宜避開人員密集的畫面（推論）。",[20,21],"public_benchmark","controlled_experiment",[23,24,25,26],"Lowest ATE on the highly dynamic TUM walking sequences, for example 1.4 cm on fr3\u002Fwalk_static and 12.7 cm on fr3\u002Fwalk_xyz versus 29.3 cm and 90.6 cm for ElasticFusion (Table II)","Accuracy comparable to ElasticFusion in static sequences (Tables I and II; Sec. VII-A)","In a 9.5 m hand-held 'selfie' sequence the final drift was 1.5 cm versus 1.03 m for ElasticFusion and 0.88 m for Co-Fusion (Sec. VII-B)","About 30 ms per frame (Sec. VIII)",[28,29,30,31,32],"Initialization needs the first 1 to 2 s to contain no more than about 20 to 30% moving elements; the method has high error (39.1 cm ATE) on fr3\u002Fwalk_halfsphere, whose start is highly dynamic (Sec. VI-A, VII-A, VIII)","Struggles if significant portions of the estimated static scene begin to move (Sec. VIII)","Static\u002Fdynamic segmentation is solved per cluster rather than per pixel, an approximation (Sec. III)","Less accurate than ElasticFusion on some static sequences, for example fr1\u002Fplant ATE 11.3 cm versus 5.3 cm (Table II)","Evaluated with a desktop GPU (GTX 1070) on a GPU-based ElasticFusion code base (Sec. V, VII)",[34],"RGB-D camera, registered RGB-D images at QVGA 320x240 (TUM Freiburg sequences and two hand-held recordings; hand-held camera model not named)",[36,37],"hand-held RGB-D camera (two authors' sequences, including a 'selfie' sequence, Sec. VII-B)","TUM Freiburg benchmark sequences (capture platform not described in the paper)","Joint minimization over the camera twist and per-cluster static scores b in [0, 1]: Cauchy-robust photometric and geometric residuals between the current RGB-D frame and a prediction rendered from the static surfel map, weighted by b, plus a residual-threshold term, spatial regularization between contiguous clusters and a depth-difference prior; IRLS for the twist with closed-form b after each iteration, coarse-to-fine","Dense direct alignment (warping current pixels into the rendered model prediction); scene split into K geometric clusters by K-means on 3D coordinates; per-pixel segmentation derived from cluster scores","discrete poses","not_applicable (RGB-D input)","none described","surfel map (Keller et al. model through the ElasticFusion implementation) in which each surfel carries a viability value accumulated as log-odds of matches with static input points; surfels with viability below 0.5 for more than 10 consecutive frames are removed and free-space violations are cleaned","none","static-background surfel map (coloured for visualization), camera trajectory and per-frame static\u002Fdynamic segmentation","Intel Core i7-3770 at 3.40 GHz with GeForce GTX 1070 GPU; about 30 ms per frame at QVGA (Sec. VII, VIII)","https:\u002F\u002Fgithub.com\u002Fraluca-scona\u002FStaticFusion","GPL-3.0 (GPL-LICENSE.txt), with reused ElasticFusion parts under the ElasticFusion licence (LICENSE.txt checked)",[50],{"relation":51,"title":52,"doi_or_url":47},"code_release","raluca-scona\u002FStaticFusion (built on the ElasticFusion code base)",{"id":5,"kind":54,"shortName":7,"title":8,"authors":55,"year":9,"venue":61,"venueType":62,"publisher":63,"volumeIssuePages":64,"doi":65,"arxivId":66,"url":67,"firstPublicDate":68,"publicationStatus":16,"metadataStatus":69,"fulltextStatus":15,"era":10,"classicReason":70,"codeUrl":47,"cluster":11,"topics":71,"mdpi":72,"verification":73,"label":6,"fulltextRoute":74,"versionRead":75,"addedByCensus":76},"method",[56,57,58,59,60],"Raluca Scona","Mariano Jaimez","Yvan R. Petillot","Maurice Fallon","Daniel Cremers","2018 IEEE International Conference on Robotics and Automation (ICRA)","conference","IEEE","pp. 3849-3856","10.1109\u002Ficra.2018.8460681",null,"https:\u002F\u002Fapi.crossref.org\u002Fworks\u002F10.1109\u002FICRA.2018.8460681","2018-05-21","metadata_verified","not_applicable",[11],false,"corrected","NTU institutional (Chrome)","IEEE Xplore HTML full text of the ICRA 2018 version of record with Tables I and II viewed as publisher images",true,[78,84],{"category":79,"model":80,"canonical":80,"role":81,"dataset":66,"specs":82,"locator":83},"compute","workstation with Intel(R) Core(TM) i7-3770 CPU at 3.40GHz and GeForce GTX 1070 GPU","compute for runtime","Ubuntu 16.04; all compared methods run on it","Sec. VII",{"category":85,"model":86,"canonical":86,"role":87,"dataset":66,"specs":88,"locator":89},"rgbd","hand-held RGB-D camera (model not reported)","method input","two recorded sequences: person interacting with objects, and a selfie sequence with the camera pointing at its carrier","Sec. VII-B",[],{"totalRows":92,"groupCount":93,"groups":94,"others":816},65,6,[95,382,631,739],{"slug":96,"group":97,"sourceId":98,"sourceLabel":99,"table":100,"selfRows":101,"metrics":102,"seqs":108,"entrants":159,"cells":168,"outcomes":376,"locators":377,"hardware":378,"wordings":379,"notes":380},"refusion2019-table-iii","refusion2019:Table III","refusion2019","Palazzolo et al., 2019","Table III",24,[103],{"label":104,"unit":105,"statistic":106,"alignment":107},"Absolute Trajectory Error (RMS) [m]","m","RMSE","not_reported",[109,113,115,117,119,121,123,125,127,129,131,133,135,137,139,141,143,145,147,149,151,153,155,157],{"dataset":110,"sequence":111,"environment":112},"Bonn RGB-D Dynamic Dataset","balloon","indoor test room with people manipulating boxes, balloons or crowding the camera",{"dataset":110,"sequence":114,"environment":112},"balloon2",{"dataset":110,"sequence":116,"environment":112},"balloon tracking",{"dataset":110,"sequence":118,"environment":112},"balloon tracking2",{"dataset":110,"sequence":120,"environment":112},"crowd",{"dataset":110,"sequence":122,"environment":112},"crowd2",{"dataset":110,"sequence":124,"environment":112},"crowd3",{"dataset":110,"sequence":126,"environment":112},"kidnapping box",{"dataset":110,"sequence":128,"environment":112},"kidnapping box2",{"dataset":110,"sequence":130,"environment":112},"moving no box",{"dataset":110,"sequence":132,"environment":112},"moving no box2",{"dataset":110,"sequence":134,"environment":112},"moving o box",{"dataset":110,"sequence":136,"environment":112},"moving o box2",{"dataset":110,"sequence":138,"environment":112},"person tracking",{"dataset":110,"sequence":140,"environment":112},"person tracking2",{"dataset":110,"sequence":142,"environment":112},"placing no box",{"dataset":110,"sequence":144,"environment":112},"placing no box2",{"dataset":110,"sequence":146,"environment":112},"placing no box3",{"dataset":110,"sequence":148,"environment":112},"placing o box",{"dataset":110,"sequence":150,"environment":112},"removing no box",{"dataset":110,"sequence":152,"environment":112},"removing no box2",{"dataset":110,"sequence":154,"environment":112},"removing o box",{"dataset":110,"sequence":156,"environment":112},"synchronous",{"dataset":110,"sequence":158,"environment":112},"synchronous2",[160,162,164,166],{"name":161,"methodId":98,"linkable":76,"proposed":76,"self":72},"Ours (ReFusion)",{"name":163,"methodId":5,"linkable":76,"proposed":72,"self":76},"SF (StaticFusion)",{"name":165,"methodId":66,"linkable":72,"proposed":72,"self":72},"DS (G) (DynaSLAM geometric)",{"name":167,"methodId":66,"linkable":72,"proposed":72,"self":72},"DS (N+G) (DynaSLAM neural network + geometric)",[169,173,176,179,182,184,186,188,190,192,194,196,198,200,202,204,206,209,211,213,215,218,220,222,224,226,228,230,232,235,237,239,240,243,245,247,248,251,253,255,257,260,262,264,266,269,271,273,275,278,280,282,283,286,288,290,292,295,297,299,301,304,306,308,310,312,314,316,318,321,323,325,327,330,332,334,336,339,341,342,343,346,348,350,351,354,356,358,360,363,365,367,369,371,372,374],[170,170,170,171,172,170,172,172,170],0,0.175,-1,[174,170,170,175,172,170,172,172,170],1,0.233,[177,170,170,178,172,170,172,172,170],2,0.05,[180,170,170,181,172,170,172,172,170],3,0.03,[170,170,174,183,172,170,172,172,170],0.254,[174,170,174,185,172,170,172,172,170],0.293,[177,170,174,187,172,170,172,172,170],0.142,[180,170,174,189,172,170,172,172,170],0.029,[170,170,177,191,172,170,172,172,170],0.302,[174,170,177,193,172,170,172,172,170],0.221,[177,170,177,195,172,170,172,172,170],0.156,[180,170,177,197,172,170,172,172,170],0.049,[170,170,180,199,172,170,172,172,170],0.322,[174,170,180,201,172,170,172,172,170],0.366,[177,170,180,203,172,170,172,172,170],0.192,[180,170,180,205,172,170,172,172,170],0.035,[170,170,207,208,172,170,172,172,170],4,0.204,[174,170,207,210,172,170,172,172,170],3.586,[177,170,207,212,172,170,172,172,170],1.065,[180,170,207,214,172,170,172,172,170],0.016,[170,170,216,217,172,170,172,172,170],5,0.155,[174,170,216,219,172,170,172,172,170],0.215,[177,170,216,221,172,170,172,172,170],1.217,[180,170,216,223,172,170,172,172,170],0.031,[170,170,93,225,172,170,172,172,170],0.137,[174,170,93,227,172,170,172,172,170],0.168,[177,170,93,229,172,170,172,172,170],0.835,[180,170,93,231,172,170,172,172,170],0.038,[170,170,233,234,172,170,172,172,170],7,0.148,[174,170,233,236,172,170,172,172,170],0.336,[177,170,233,238,172,170,172,172,170],0.026,[180,170,233,189,172,170,172,172,170],[170,170,241,242,172,170,172,172,170],8,0.161,[174,170,241,244,172,170,172,172,170],0.263,[177,170,241,246,172,170,172,172,170],0.033,[180,170,241,205,172,170,172,172,170],[170,170,249,250,172,170,172,172,170],9,0.071,[174,170,249,252,172,170,172,172,170],0.141,[177,170,249,254,172,170,172,172,170],0.317,[180,170,249,256,172,170,172,172,170],0.232,[170,170,258,259,172,170,172,172,170],10,0.179,[174,170,258,261,172,170,172,172,170],0.364,[177,170,258,263,172,170,172,172,170],0.052,[180,170,258,265,172,170,172,172,170],0.039,[170,170,267,268,172,170,172,172,170],11,0.343,[174,170,267,270,172,170,172,172,170],0.331,[177,170,267,272,172,170,172,172,170],0.544,[180,170,267,274,172,170,172,172,170],0.044,[170,170,276,277,172,170,172,172,170],12,0.528,[174,170,276,279,172,170,172,172,170],0.309,[177,170,276,281,172,170,172,172,170],0.589,[180,170,276,244,172,170,172,172,170],[170,170,284,285,172,170,172,172,170],13,0.289,[174,170,284,287,172,170,172,172,170],0.484,[177,170,284,289,172,170,172,172,170],0.714,[180,170,284,291,172,170,172,172,170],0.061,[170,170,293,294,172,170,172,172,170],14,0.463,[174,170,293,296,172,170,172,172,170],0.626,[177,170,293,298,172,170,172,172,170],0.817,[180,170,293,300,172,170,172,172,170],0.078,[170,170,302,303,172,170,172,172,170],15,0.106,[174,170,302,305,172,170,172,172,170],0.125,[177,170,302,307,172,170,172,172,170],0.645,[180,170,302,309,172,170,172,172,170],0.575,[170,170,311,252,172,170,172,172,170],16,[174,170,311,313,172,170,172,172,170],0.177,[177,170,311,315,172,170,172,172,170],0.027,[180,170,311,317,172,170,172,172,170],0.021,[170,170,319,320,172,170,172,172,170],17,0.174,[174,170,319,322,172,170,172,172,170],0.256,[177,170,319,324,172,170,172,172,170],0.327,[180,170,319,326,172,170,172,172,170],0.058,[170,170,328,329,172,170,172,172,170],18,0.571,[174,170,328,331,172,170,172,172,170],0.33,[177,170,328,333,172,170,172,172,170],0.267,[180,170,328,335,172,170,172,172,170],0.255,[170,170,337,338,172,170,172,172,170],19,0.041,[174,170,337,340,172,170,172,172,170],0.136,[177,170,337,214,172,170,172,172,170],[180,170,337,214,172,170,172,172,170],[170,170,344,345,172,170,172,172,170],20,0.111,[174,170,344,347,172,170,172,172,170],0.129,[177,170,344,349,172,170,172,172,170],0.022,[180,170,344,317,172,170,172,172,170],[170,170,352,353,172,170,172,172,170],21,0.222,[174,170,352,355,172,170,172,172,170],0.334,[177,170,352,357,172,170,172,172,170],0.362,[180,170,352,359,172,170,172,172,170],0.291,[170,170,361,362,172,170,172,172,170],22,0.441,[174,170,361,364,172,170,172,172,170],0.446,[177,170,361,366,172,170,172,172,170],0.977,[180,170,361,368,172,170,172,172,170],0.015,[170,170,370,349,172,170,172,172,170],23,[174,170,370,315,172,170,172,172,170],[177,170,370,373,172,170,172,172,170],0.887,[180,170,370,375,172,170,172,172,170],0.009,[],[100],[],[],[381],"Bonn RGB-D Dynamic Dataset (24 highly dynamic scenes, ASUS Xtion Pro LIVE, OptiTrack Prime 13 ground truth); ATE RMS; 'o box' = obstructing box, 'no box' = nonobstructing box; all methods run by the authors with default parameters",{"slug":383,"group":384,"sourceId":5,"sourceLabel":6,"table":385,"selfRows":361,"metrics":386,"seqs":393,"entrants":418,"cells":429,"outcomes":624,"locators":626,"hardware":627,"wordings":628,"notes":629},"staticfusion2018-table-i","staticfusion2018:Table I","Table I",[387,390],{"label":388,"unit":389,"statistic":106,"alignment":107},"Trans. RPE RMSE (cm\u002Fs)","cm\u002Fs",{"label":391,"unit":392,"statistic":106,"alignment":107},"Rot. RPE RMSE (deg\u002Fs)","deg\u002Fs",[394,398,400,402,404,406,408,410,412,414,416],{"dataset":395,"sequence":396,"environment":397},"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":395,"sequence":399,"environment":397},"fr1\u002Fdesk",{"dataset":395,"sequence":401,"environment":397},"fr1\u002Fdesk2",{"dataset":395,"sequence":403,"environment":397},"fr1\u002Fplant",{"dataset":395,"sequence":405,"environment":397},"fr3\u002Fsit_static",{"dataset":395,"sequence":407,"environment":397},"fr3\u002Fsit_xyz",{"dataset":395,"sequence":409,"environment":397},"fr3\u002Fsit_halfsphere",{"dataset":395,"sequence":411,"environment":397},"fr3\u002Fwalk_static",{"dataset":395,"sequence":413,"environment":397},"fr3\u002Fwalk_xyz",{"dataset":395,"sequence":415,"environment":397},"fr3\u002Fwalk_halfsphere*",{"dataset":395,"sequence":417,"environment":397},"fr3\u002Fwalk_halfsphere",[419,421,424,426,428],{"name":420,"methodId":66,"linkable":72,"proposed":72,"self":72},"VO-SF (Jaimez et al. joint visual odometry and scene flow)",{"name":422,"methodId":423,"linkable":76,"proposed":72,"self":72},"EF (ElasticFusion)","elasticfusion2015",{"name":425,"methodId":66,"linkable":72,"proposed":72,"self":72},"CF (Co-Fusion)",{"name":427,"methodId":66,"linkable":72,"proposed":72,"self":72},"BaMVO (Kim et al.)",{"name":163,"methodId":5,"linkable":76,"proposed":76,"self":76},[430,432,434,436,437,438,440,442,443,444,445,447,449,451,452,453,455,456,458,459,461,463,465,467,468,469,471,473,475,477,479,481,483,484,486,487,489,491,493,495,497,499,500,502,504,506,508,510,512,513,514,516,518,520,522,524,525,527,529,530,532,534,536,538,539,541,543,545,547,548,550,551,553,555,556,558,560,562,564,566,568,570,572,573,575,577,579,581,583,585,587,589,591,593,595,597,599,600,602,604,606,608,609,611,612,614,616,618,620,622],[170,170,170,431,172,170,172,172,170],2.1,[174,170,170,433,172,170,172,172,170],1.9,[177,170,170,435,172,170,172,172,170],2.3,[180,170,170,66,170,170,172,172,170],[207,170,170,435,172,170,172,172,170],[170,170,174,439,172,170,172,172,170],3.7,[174,170,174,441,172,170,172,172,170],2.9,[177,170,174,249,172,170,172,172,170],[180,170,174,66,170,170,172,172,170],[207,170,174,180,172,170,172,172,170],[170,170,177,446,172,170,172,172,170],5.4,[174,170,177,448,172,170,172,172,170],7.2,[177,170,177,450,172,170,172,172,170],9.2,[180,170,177,66,170,170,172,172,170],[207,170,177,216,172,170,172,172,170],[170,170,180,454,172,170,172,172,170],6.1,[174,170,180,216,172,170,172,172,170],[177,170,180,457,172,170,172,172,170],8.9,[180,170,180,66,170,170,172,172,170],[207,170,180,460,172,170,172,172,170],10.4,[170,170,207,462,172,170,172,172,170],2.4,[174,170,207,464,172,170,172,172,170],0.9,[177,170,207,466,172,170,172,172,170],1.1,[180,170,207,462,172,170,172,172,170],[207,170,207,466,172,170,172,172,170],[170,170,216,470,172,170,172,172,170],5.7,[174,170,216,472,172,170,172,172,170],1.6,[177,170,216,474,172,170,172,172,170],2.7,[180,170,216,476,172,170,172,172,170],4.8,[207,170,216,478,172,170,172,172,170],2.8,[170,170,93,480,172,170,172,172,170],7.5,[174,170,93,482,172,170,172,172,170],17.2,[177,170,93,180,172,170,172,172,170],[180,170,93,485,172,170,172,172,170],5.8,[207,170,93,180,172,170,172,172,170],[170,170,233,488,172,170,172,172,170],10.1,[174,170,233,490,172,170,172,172,170],26,[177,170,233,492,172,170,172,172,170],22.4,[180,170,233,494,172,170,172,172,170],13.3,[207,170,233,496,172,170,172,172,170],1.3,[170,170,241,498,172,170,172,172,170],27.7,[174,170,241,101,172,170,172,172,170],[177,170,241,501,172,170,172,172,170],32.9,[180,170,241,503,172,170,172,172,170],23.2,[207,170,241,505,172,170,172,172,170],12.1,[170,170,249,507,172,170,172,172,170],24.8,[174,170,249,509,172,170,172,172,170],16.3,[177,170,249,511,172,170,172,172,170],31.1,[180,170,249,66,170,170,172,172,170],[207,170,249,216,172,170,172,172,170],[170,170,258,515,172,170,172,172,170],33.5,[174,170,258,517,172,170,172,172,170],20.5,[177,170,258,519,172,170,172,172,170],40,[180,170,258,521,172,170,172,172,170],17.3,[207,170,258,523,172,170,172,172,170],20.7,[170,174,170,174,172,170,172,172,170],[174,174,170,526,172,170,172,172,170],0.91,[177,174,170,528,172,170,172,172,170],1.34,[180,174,170,66,170,170,172,172,170],[207,174,170,531,172,170,172,172,170],1.42,[170,174,174,533,172,170,172,172,170],1.77,[174,174,174,535,172,170,172,172,170],1.48,[177,174,174,537,172,170,172,172,170],4.49,[180,174,174,66,170,170,172,172,170],[207,174,174,540,172,170,172,172,170],2.17,[170,174,177,542,172,170,172,172,170],2.45,[174,174,177,544,172,170,172,172,170],4.07,[177,174,177,546,172,170,172,172,170],4.79,[180,174,177,66,170,170,172,172,170],[207,174,177,549,172,170,172,172,170],3.39,[170,174,180,177,172,170,172,172,170],[174,174,180,552,172,170,172,172,170],1.58,[177,174,180,554,172,170,172,172,170],3.02,[180,174,180,66,170,170,172,172,170],[207,174,180,557,172,170,172,172,170],3.16,[170,174,207,559,172,170,172,172,170],0.71,[174,174,207,561,172,170,172,172,170],0.3,[177,174,207,563,172,170,172,172,170],0.44,[180,174,207,565,172,170,172,172,170],0.69,[207,174,207,567,172,170,172,172,170],0.43,[170,174,216,569,172,170,172,172,170],1.44,[174,174,216,571,172,170,172,172,170],0.59,[177,174,216,174,172,170,172,172,170],[180,174,216,574,172,170,172,172,170],1.38,[207,174,216,576,172,170,172,172,170],0.92,[170,174,93,578,172,170,172,172,170],2.98,[174,174,93,580,172,170,172,172,170],4.56,[177,174,93,582,172,170,172,172,170],1.92,[180,174,93,584,172,170,172,172,170],2.88,[207,174,93,586,172,170,172,172,170],2.11,[170,174,233,588,172,170,172,172,170],1.68,[174,174,233,590,172,170,172,172,170],4.77,[177,174,233,592,172,170,172,172,170],4.01,[180,174,233,594,172,170,172,172,170],2.08,[207,174,233,596,172,170,172,172,170],0.38,[170,174,241,598,172,170,172,172,170],5.11,[174,174,241,546,172,170,172,172,170],[177,174,241,601,172,170,172,172,170],5.55,[180,174,241,603,172,170,172,172,170],4.39,[207,174,241,605,172,170,172,172,170],2.66,[170,174,249,607,172,170,172,172,170],5.49,[174,174,249,470,172,170,172,172,170],[177,174,249,610,172,170,172,172,170],8.45,[180,174,249,66,170,170,172,172,170],[207,174,249,613,172,170,172,172,170],2.18,[170,174,258,615,172,170,172,172,170],6.69,[174,174,258,617,172,170,172,172,170],6.41,[177,174,258,619,172,170,172,172,170],13.02,[180,174,258,621,172,170,172,172,170],4.28,[207,174,258,623,172,170,172,172,170],5.04,[625],"not reported (BaMVO shown only for sequences evaluated in its original publication)",[385],[],[],[630],"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":632,"group":633,"sourceId":5,"sourceLabel":6,"table":634,"selfRows":267,"metrics":635,"seqs":639,"entrants":651,"cells":656,"outcomes":733,"locators":734,"hardware":735,"wordings":736,"notes":737},"staticfusion2018-table-ii","staticfusion2018:Table II","Table II",[636],{"label":637,"unit":638,"statistic":106,"alignment":107},"Trans. ATE RMSE (cm)","cm",[640,641,642,643,644,645,646,647,648,649,650],{"dataset":395,"sequence":396,"environment":397},{"dataset":395,"sequence":399,"environment":397},{"dataset":395,"sequence":401,"environment":397},{"dataset":395,"sequence":403,"environment":397},{"dataset":395,"sequence":405,"environment":397},{"dataset":395,"sequence":407,"environment":397},{"dataset":395,"sequence":409,"environment":397},{"dataset":395,"sequence":411,"environment":397},{"dataset":395,"sequence":413,"environment":397},{"dataset":395,"sequence":415,"environment":397},{"dataset":395,"sequence":417,"environment":397},[652,653,654,655],{"name":420,"methodId":66,"linkable":72,"proposed":72,"self":72},{"name":422,"methodId":423,"linkable":76,"proposed":72,"self":72},{"name":425,"methodId":66,"linkable":72,"proposed":72,"self":72},{"name":163,"methodId":5,"linkable":76,"proposed":76,"self":76},[657,659,661,663,664,666,667,669,670,672,673,675,677,679,681,683,685,686,688,689,690,692,694,695,696,697,699,701,702,704,706,708,709,711,713,715,717,719,721,723,725,727,729,731],[170,170,170,658,172,170,172,172,170],5.1,[174,170,170,660,172,170,172,172,170],1.2,[177,170,170,662,172,170,172,172,170],1.4,[180,170,170,662,172,170,172,172,170],[170,170,174,665,172,170,172,172,170],5.6,[174,170,174,431,172,170,172,172,170],[177,170,174,668,172,170,172,172,170],17.7,[180,170,174,435,172,170,172,172,170],[170,170,177,671,172,170,172,172,170],17.4,[174,170,177,470,172,170,172,172,170],[177,170,177,674,172,170,172,172,170],16.8,[180,170,177,676,172,170,172,172,170],5.2,[170,170,180,678,172,170,172,172,170],7.8,[174,170,180,680,172,170,172,172,170],5.3,[177,170,180,682,172,170,172,172,170],12.6,[180,170,180,684,172,170,172,172,170],11.3,[170,170,207,441,172,170,172,172,170],[174,170,207,687,172,170,172,172,170],0.8,[177,170,207,466,172,170,172,172,170],[180,170,207,496,172,170,172,172,170],[170,170,216,691,172,170,172,172,170],11.1,[174,170,216,693,172,170,172,172,170],2.2,[177,170,216,474,172,170,172,172,170],[180,170,216,207,172,170,172,172,170],[170,170,93,328,172,170,172,172,170],[174,170,93,698,172,170,172,172,170],42.8,[177,170,93,700,172,170,172,172,170],3.6,[180,170,93,207,172,170,172,172,170],[170,170,233,703,172,170,172,172,170],32.7,[174,170,233,705,172,170,172,172,170],29.3,[177,170,233,707,172,170,172,172,170],55.1,[180,170,233,662,172,170,172,172,170],[170,170,241,710,172,170,172,172,170],87.4,[174,170,241,712,172,170,172,172,170],90.6,[177,170,241,714,172,170,172,172,170],69.6,[180,170,241,716,172,170,172,172,170],12.7,[170,170,249,718,172,170,172,172,170],48.2,[174,170,249,720,172,170,172,172,170],48.6,[177,170,249,722,172,170,172,172,170],75.6,[180,170,249,724,172,170,172,172,170],6.3,[170,170,258,726,172,170,172,172,170],73.9,[174,170,258,728,172,170,172,172,170],63.8,[177,170,258,730,172,170,172,172,170],80.3,[180,170,258,732,172,170,172,172,170],39.1,[],[634],[],[],[738],"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",{"slug":740,"group":741,"sourceId":98,"sourceLabel":99,"table":634,"selfRows":93,"metrics":742,"seqs":744,"entrants":759,"cells":766,"outcomes":809,"locators":811,"hardware":812,"wordings":813,"notes":814},"refusion2019-table-ii","refusion2019:Table II",[743],{"label":104,"unit":105,"statistic":106,"alignment":107},[745,749,751,753,755,757],{"dataset":746,"sequence":747,"environment":748},"TUM RGB-D","sitting static","indoor office with seated or walking people, handheld RGB-D",{"dataset":746,"sequence":750,"environment":748},"sitting xyz",{"dataset":746,"sequence":752,"environment":748},"sitting halfsphere",{"dataset":746,"sequence":754,"environment":748},"walking static",{"dataset":746,"sequence":756,"environment":748},"walking xyz",{"dataset":746,"sequence":758,"environment":748},"walking halfsphere",[760,761,762,763,764],{"name":161,"methodId":98,"linkable":76,"proposed":76,"self":72},{"name":163,"methodId":5,"linkable":76,"proposed":72,"self":76},{"name":165,"methodId":66,"linkable":72,"proposed":72,"self":72},{"name":167,"methodId":66,"linkable":72,"proposed":72,"self":72},{"name":765,"methodId":66,"linkable":72,"proposed":72,"self":72},"MF (MaskFusion, values from its paper)",[767,768,770,771,773,774,776,777,778,779,780,782,783,785,787,788,789,790,791,792,793,795,797,799,800,802,803,805,807,808],[170,170,170,375,172,170,172,172,170],[174,170,170,769,172,170,172,172,170],0.014,[177,170,170,375,172,170,172,172,170],[180,170,170,772,172,170,172,172,170],0.007,[207,170,170,317,172,170,172,172,170],[170,170,174,775,172,170,172,172,170],0.04,[174,170,174,265,172,170,172,172,170],[177,170,174,375,172,170,172,172,170],[180,170,174,368,172,170,172,172,170],[207,170,174,223,172,170,172,172,170],[170,170,177,781,172,170,172,172,170],0.11,[174,170,177,338,172,170,172,172,170],[177,170,177,784,172,170,172,172,170],0.017,[180,170,177,786,172,170,172,172,170],0.028,[207,170,177,263,172,170,172,172,170],[170,170,180,784,172,170,172,172,170],[174,170,180,368,172,170,172,172,170],[177,170,180,769,172,170,172,172,170],[180,170,180,772,172,170,172,172,170],[207,170,180,205,172,170,172,172,170],[170,170,207,794,172,170,172,172,170],0.099,[174,170,207,796,172,170,172,172,170],0.093,[177,170,207,798,172,170,172,172,170],0.085,[180,170,207,784,172,170,172,172,170],[207,170,207,801,172,170,172,172,170],0.104,[170,170,216,801,172,170,172,172,170],[174,170,216,804,170,170,172,172,170],0.681,[177,170,216,806,172,170,172,172,170],0.084,[180,170,216,238,172,170,172,172,170],[207,170,216,303,172,170,172,172,170],[810],"other: StaticFusion lost track at the start of this sequence because of excessive dynamic elements (Sec. IV-A)",[634],[],[],[815],"TUM RGB-D dynamic scenes; ATE RMS; ReFusion uses virtual depth from 10 frames (about 0.3 s delay) to fill invalid depth; ReFusion, SF and MF are dense, DynaSLAM is feature-based; StaticFusion lost track on walking halfsphere",[817,823],{"group":818,"slug":819,"sourceLabel":6,"table":820,"selfRows":174,"datasets":821},"staticfusion2018:Text Sec.VII-B","staticfusion2018-text-sec-vii-b","Text Sec.VII-B",[822],"authors' hand-held selfie sequence",{"group":824,"slug":825,"sourceLabel":6,"table":826,"selfRows":174,"datasets":827},"staticfusion2018:Text Sec.VIII","staticfusion2018-text-sec-viii","Text Sec.VIII",[107],1790510660449]