[{"data":1,"prerenderedAt":610},["ShallowReactive",2],{"method-zhang2024globalbimreg":3},{"method":4,"reference":53,"equipment":73,"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":29,"sensors":38,"platform":41,"estimator":43,"association":44,"timeModel":45,"deskew":45,"loopClosure":45,"globalOptimization":45,"mapRepresentation":46,"prior":47,"outputGeometry":48,"compute":49,"codeUrl":50,"codeLicense":51,"relatedVersions":52},"zhang2024globalbimreg","Zhang et al., 2024b","Global BIM-point registration and association","Global BIM-point cloud registration and association for construction progress monitoring",2024,"recent","C11b","downstream_engineering_task","作者把 BIM 構件以構造實體幾何（CSG）拆解並以解析距離場表示，避免取樣造成資訊損失。粗配準以平面基元對 BIM 面在重力軸對齊下搜尋對應，並以剛體動力學模擬驗證幾何一致性；精配準則交替更新位姿與逐點對應權重，並以鄰近性、法向與構件存在與否截斷權重，使臨時材料與未施作構件不誤導配準。模擬採 ISPRS 室內建模基準（含手持與背包掃描）。","Registers as-is point clouds to BIM globally using distance-field BIM primitives and jointly refines pose and BIM-point association with existence-aware weights to support progress monitoring.","full_text_reviewed","peer_reviewed_published","main_body","實測於香港城市大學賽馬會一健康大樓施工工地 06 至 12 樓（CR Construction 協助，每層約 80 m × 50 m），以手持感測套件上的 Ouster OS0-128 蒐集資料，再以 FAST-LIO2 逐層重建點雲，BIM 為 LOD 300。評估用的參考值不是直接量測的點位誤差，而是以工程師現地量測的 3 至 4 個結構特徵點（GCP）作為同名點，在 CloudCompare v2.13 alpha 人工粗配準後再做點對網格精配準所得的轉換；屬施工中工地且使用 SLAM 點雲。",[20,21,22],"public_benchmark","real_construction_site","independent_reference",[24,25,26,27,28],"coarse registration median TE 0.053 m and RE 0.272 deg over the successful cases of 250 perturbed samples (Table 1)","fine registration median TE 0.0246 m vs 0.0422 m for point-to-point ICP (Table 2)","100% coarse success for alpha_r >= 0.5 deg and alpha_t >= 0.4 m, unlike all ten baselines (Sec. 4.1.2, Fig. 10)","on seven floors of an active site, fine-registration errors of 0.009-0.203 deg and 0.032-0.107 m relative to the CloudCompare reference, about 0.05 deg and 0.058 m on average (Table 4)","per-point association separates rebar, glass, barriers, temporary materials, pipes and boxes from built structures and flags unbuilt decoration walls (Sec. 4.2.2, Fig. 15)",[30,31,32,33,34,35,36,37],"drift errors in the FAST-LIO2 reconstruction caused some wall points to receive low association levels (floors 07 and 12); authors suggest a high-precision laser scanner (Sec. 4.2.2)","geometry-only association: barriers close to walls can be associated with the wall even with normal verification (Sec. 4.2.2)","only regular human-made structures are modelled; MEP objects are not included (Sec. 4.2.2)","offline only; point clouds with few planar segments cannot be registered (Sec. 4.2.2)","coarse registration slower than PLADE and RANSAC in simulation (64.2 s vs 8.85 s and 27.27 s) (Sec. 4.1.2)","coarse precision drops for sparse or partial clouds from early construction stages (Table 3)","(inference) the real-site reference is itself a manual CloudCompare registration seeded by 3-4 GCPs, so centimetre-level differences are not independently verified","(inference) assumes gravity axis known and planar primitives dominant",[39,40],"real site: handheld sensor suite with Ouster OS0-128 LiDAR (clouds built with FAST-LIO2)","simulation: ISPRS indoor modelling benchmark clouds from stationary, handheld and backpack scanners",[42],"handheld","primitive-level coarse registration (orientation hypotheses using gravity, correspondence tree, geometric constraint filter, rigid-body dynamics simulator) + point-level Gauss-Newton fine registration with Geman-McClure weights (Sec. 3.2-3.3)","plane primitives to BIM distance fields; per-point weights truncated by proximity, normal consistency and element existence (Sec. 3.3.2)","not_applicable","BIM as CSG-decomposed analytic distance fields; input point cloud","BIM (IFC) split into IfcWall, IfcSlab, IfcColumn, IfcBeam (and IfcCovering on site) and decomposed into convex CSG primitives with analytic distance fields; LOD 200-300 in simulation, LOD 300 on site; gravity axis assumed known in both frames, reducing 24 orientation hypotheses to 4 (Sec. 3.1, 3.2.1, 4.1.1, 4.2.1)","BIM-aligned point cloud with per-point association weights (progress existence check)","Intel Core i9-12900H CPU; offline. Simulation: coarse registration 64.2 s on average (PLADE 8.85 s, RANSAC 27.27 s), fine registration 16.57 s (Sec. 4.1.2, Table 2). Real site: coarse about 2 min 45 s per floor, fine under 50 s (pose refinement 18.08 s plus association 30.66 s) (Sec. 4.2.2, Table 4); verification uses multi-threading and the Tsit5 ODE solver",null,"not_verified",[],{"id":5,"kind":54,"shortName":7,"title":8,"authors":55,"year":9,"venue":60,"venueType":61,"publisher":62,"volumeIssuePages":63,"doi":64,"arxivId":50,"url":65,"firstPublicDate":66,"publicationStatus":16,"metadataStatus":67,"fulltextStatus":15,"era":10,"classicReason":45,"codeUrl":50,"cluster":11,"topics":68,"mdpi":69,"verification":70,"label":6,"fulltextRoute":71,"versionRead":72,"addedByCensus":69},"method",[56,57,58,59],"Yinqiang Zhang","Liang Lu","Xiaowei Luo","Jia Pan","Automation in Construction","journal","Elsevier","168 (Part A), 105796","10.1016\u002Fj.autcon.2024.105796","https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0926580524005326","2024-10-01","metadata_verified",[11],false,"corrected","NTU institutional (Chrome)","version of record, ScienceDirect HTML (Automation in Construction 168 Part A, 105796, 1 December 2024), read in full",[74,80,86,93,96],{"category":75,"model":76,"canonical":76,"role":77,"dataset":50,"specs":78,"locator":79},"lidar","Ouster OS0-128","method input","on a handheld sensor suite; operator walked each floor; clouds reconstructed per floor with FAST-LIO2","Sec. 4.2.1",{"category":81,"model":82,"canonical":82,"role":83,"dataset":50,"specs":84,"locator":85},"compute","Intel(R) Core(TM) i9-12900H CPU","compute for runtime","all experiments","Sec. 4",{"category":87,"model":88,"canonical":88,"role":89,"dataset":90,"specs":91,"locator":92},"tls_scanner","not_reported (stationary laser scanner)","dataset sensor","ISPRS benchmark on indoor modelling","not_reported","Sec. 4.1.1",{"category":94,"model":95,"canonical":95,"role":89,"dataset":90,"specs":91,"locator":92},"mobile_scanner_device","not_reported (handheld and backpack laser scanners)",{"category":97,"model":98,"canonical":98,"role":99,"dataset":50,"specs":100,"locator":79},"other","not_reported (engineers' on-site measurement of 3-4 structural landmarks as GCPs)","reference or ground truth","GCPs at different heights about 20 m apart; used with CloudCompare v2.13 alpha to build the reference registration",[],{"totalRows":103,"groupCount":104,"groups":105,"others":598},88,6,[106,244,335,525],{"slug":107,"group":108,"sourceId":5,"sourceLabel":6,"table":109,"selfRows":110,"metrics":111,"seqs":124,"entrants":141,"cells":147,"outcomes":237,"locators":238,"hardware":239,"wordings":241,"notes":242},"zhang2024globalbimreg-table-4","zhang2024globalbimreg:Table 4","Table 4",42,[112,116,118,121],{"label":113,"unit":114,"statistic":91,"alignment":115},"Time (s), coarse registration","s","none",{"label":117,"unit":114,"statistic":91,"alignment":115},"Time (s), fine registration",{"label":119,"unit":120,"statistic":91,"alignment":115},"delta_r, rotation error","deg",{"label":122,"unit":123,"statistic":91,"alignment":115},"delta_t, translation error","m",[125,129,131,133,135,137,139],{"dataset":126,"sequence":127,"environment":128},"Jockey Club One Health Tower site data (self-collected)","Floor 06","active high-rise construction site, building interiors (Hong Kong)",{"dataset":126,"sequence":130,"environment":128},"Floor 07",{"dataset":126,"sequence":132,"environment":128},"Floor 08",{"dataset":126,"sequence":134,"environment":128},"Floor 09",{"dataset":126,"sequence":136,"environment":128},"Floor 10",{"dataset":126,"sequence":138,"environment":128},"Floor 11",{"dataset":126,"sequence":140,"environment":128},"Floor 12",[142,145],{"name":143,"methodId":5,"linkable":144,"proposed":144,"self":144},"Ours (coarse registration)",true,{"name":146,"methodId":5,"linkable":144,"proposed":144,"self":144},"Ours (fine registration)",[148,152,155,158,161,163,165,167,169,171,173,175,176,178,180,182,184,186,188,190,192,194,196,198,200,203,205,207,209,210,212,215,217,219,221,223,225,227,229,231,233,235],[149,149,149,150,151,149,149,151,149],0,162.06,-1,[153,153,149,154,151,149,149,151,149],1,45.85,[149,156,149,157,151,149,151,151,149],2,0.039,[149,159,149,160,151,149,151,151,149],3,0.062,[153,156,149,162,151,149,151,151,149],0.012,[153,159,149,164,151,149,151,151,149],0.045,[149,149,153,166,151,149,149,151,149],129.73,[153,153,153,168,151,149,149,151,149],55.34,[149,156,153,170,151,149,151,151,149],0.327,[149,159,153,172,151,149,151,151,149],0.064,[153,156,153,174,151,149,151,151,149],0.009,[153,159,153,172,151,149,151,151,149],[149,149,156,177,151,149,149,151,149],121.94,[153,153,156,179,151,149,149,151,149],49.54,[149,156,156,181,151,149,151,151,149],0.011,[149,159,156,183,151,149,151,151,149],0.067,[153,156,156,185,151,149,151,151,149],0.023,[153,159,156,187,151,149,151,151,149],0.056,[149,149,159,189,151,149,149,151,149],112.06,[153,153,159,191,151,149,149,151,149],52.88,[149,156,159,193,151,149,151,151,149],0.269,[149,159,159,195,151,149,151,151,149],0.089,[153,156,159,197,151,149,151,151,149],0.085,[153,159,159,199,151,149,151,151,149],0.057,[149,149,201,202,151,149,149,151,149],4,301.95,[153,153,201,204,151,149,149,151,149],43,[149,156,201,206,151,149,151,151,149],0.081,[149,159,201,208,151,149,151,151,149],0.054,[153,156,201,162,151,149,151,151,149],[153,159,201,211,151,149,151,151,149],0.032,[149,149,213,214,151,149,149,151,149],5,182.58,[153,153,213,216,151,149,149,151,149],47.52,[149,156,213,218,151,149,151,151,149],0.097,[149,159,213,220,151,149,151,151,149],0.061,[153,156,213,222,151,149,151,151,149],0.01,[153,159,213,224,151,149,151,151,149],0.043,[149,149,104,226,151,149,149,151,149],147.39,[153,153,104,228,151,149,149,151,149],48.73,[149,156,104,230,151,149,151,151,149],0.38,[149,159,104,232,151,149,151,151,149],0.142,[153,156,104,234,151,149,151,151,149],0.203,[153,159,104,236,151,149,151,151,149],0.107,[],[109],[240],"Intel Core i9-12900H CPU",[],[243],"Jockey Club One Health Tower construction site, floors 06-12; handheld Ouster OS0-128 clouds reconstructed per floor with FAST-LIO2 and registered to a LOD 300 BIM without knowing the floor number; errors relative to a manual CloudCompare registration seeded by 3-4 engineer-measured GCP pairs and refined point-to-mesh",{"slug":245,"group":246,"sourceId":5,"sourceLabel":6,"table":247,"selfRows":248,"metrics":249,"seqs":255,"entrants":271,"cells":274,"outcomes":329,"locators":330,"hardware":331,"wordings":332,"notes":333},"zhang2024globalbimreg-table-3","zhang2024globalbimreg:Table 3","Table 3",28,[250,253],{"label":251,"unit":120,"statistic":252,"alignment":115},"RE-Mean, rotation error","mean",{"label":254,"unit":123,"statistic":252,"alignment":115},"TE-Mean, translation error",[256,259,261,263,265,267,269],{"dataset":90,"sequence":257,"environment":258},"Raw","building interiors from the ISPRS indoor modelling benchmark (Models 01-05)",{"dataset":90,"sequence":260,"environment":258},"voxel 0.01 m",{"dataset":90,"sequence":262,"environment":258},"voxel 0.025 m",{"dataset":90,"sequence":264,"environment":258},"voxel 0.05 m",{"dataset":90,"sequence":266,"environment":258},"Case 01 (partial cloud, temporal stage)",{"dataset":90,"sequence":268,"environment":258},"Case 02 (partial cloud, temporal stage)",{"dataset":90,"sequence":270,"environment":258},"Case 03 (partial cloud, temporal stage)",[272,273],{"name":143,"methodId":5,"linkable":144,"proposed":144,"self":144},{"name":146,"methodId":5,"linkable":144,"proposed":144,"self":144},[275,277,279,281,283,285,287,289,291,293,295,296,298,300,302,304,306,308,310,312,314,316,318,320,322,323,325,327],[149,149,149,276,151,149,151,151,149],0.125,[149,153,149,278,151,149,151,151,149],0.265,[153,149,149,280,151,149,151,151,149],0.06,[153,153,149,282,151,149,151,151,149],0.11,[149,149,153,284,151,149,151,151,149],0.122,[149,153,153,286,151,149,151,151,149],0.26,[153,149,153,288,151,149,151,151,149],0.078,[153,153,153,290,151,149,151,151,149],0.117,[149,149,156,292,151,149,151,151,149],0.151,[149,153,156,294,151,149,151,151,149],0.315,[153,149,156,197,151,149,151,151,149],[153,153,156,297,151,149,151,151,149],0.129,[149,149,159,299,151,149,151,151,149],0.217,[149,153,159,301,151,149,151,151,149],0.403,[153,149,159,303,151,149,151,151,149],0.072,[153,153,159,305,151,149,151,151,149],0.126,[149,149,201,307,151,149,151,151,149],0.09,[149,153,201,309,151,149,151,151,149],0.288,[153,149,201,311,151,149,151,151,149],0.026,[153,153,201,313,151,149,151,151,149],0.127,[149,149,213,315,151,149,151,151,149],0.149,[149,153,213,317,151,149,151,151,149],0.411,[153,149,213,319,151,149,151,151,149],0.02,[153,153,213,321,151,149,151,151,149],0.037,[149,149,104,220,151,149,151,151,149],[149,153,104,324,151,149,151,151,149],0.182,[153,149,104,326,151,149,151,151,149],0.015,[153,153,104,328,151,149,151,151,149],0.079,[],[247],[],[],[334],"Sensitivity of the proposed method: point clouds voxel-downsampled at different sizes, and partial clouds simulating temporal construction stages (Cases 01-03 from Models 01 and 02); mean errors",{"slug":336,"group":337,"sourceId":5,"sourceLabel":6,"table":338,"selfRows":104,"metrics":339,"seqs":353,"entrants":356,"cells":382,"outcomes":519,"locators":520,"hardware":521,"wordings":522,"notes":523},"zhang2024globalbimreg-table-1","zhang2024globalbimreg:Table 1","Table 1",[340,343,345,347,349,351],{"label":341,"unit":120,"statistic":342,"alignment":115},"RE_50, rotation error 50th percentile","median",{"label":344,"unit":120,"statistic":91,"alignment":115},"RE_75, rotation error 75th percentile",{"label":346,"unit":120,"statistic":91,"alignment":115},"RE_95, rotation error 95th percentile",{"label":348,"unit":123,"statistic":342,"alignment":115},"TE_50, translation error 50th percentile",{"label":350,"unit":123,"statistic":91,"alignment":115},"TE_75, translation error 75th percentile",{"label":352,"unit":123,"statistic":91,"alignment":115},"TE_95, translation error 95th percentile",[354],{"dataset":90,"sequence":355,"environment":258},"Models 01-05 (250 samples)",[357,359,361,364,366,369,372,374,376,378,380],{"name":358,"methodId":50,"linkable":69,"proposed":69,"self":69},"GMMTree (initialised with FPFH-RANSAC)",{"name":360,"methodId":50,"linkable":69,"proposed":69,"self":69},"FilterReg (initialised with FPFH-RANSAC)",{"name":362,"methodId":363,"linkable":144,"proposed":69,"self":69},"GO-ICP","yang2016goicp",{"name":365,"methodId":50,"linkable":69,"proposed":69,"self":69},"Super4PCS",{"name":367,"methodId":368,"linkable":144,"proposed":69,"self":69},"FGR","zhou2016fgr",{"name":370,"methodId":371,"linkable":144,"proposed":69,"self":69},"RANSAC (FPFH features)","fischler1981ransac",{"name":373,"methodId":50,"linkable":69,"proposed":69,"self":69},"RMMG",{"name":375,"methodId":50,"linkable":69,"proposed":69,"self":69},"PLADE",{"name":377,"methodId":50,"linkable":69,"proposed":69,"self":69},"DCP",{"name":379,"methodId":50,"linkable":69,"proposed":69,"self":69},"PointNetLK",{"name":381,"methodId":5,"linkable":144,"proposed":144,"self":144},"Ours (primitive-level coarse registration)",[383,385,387,389,391,393,395,397,399,401,403,405,407,409,411,413,415,417,419,421,423,425,427,429,431,433,435,437,439,441,443,445,447,449,451,453,455,457,459,461,463,465,467,470,472,474,476,478,480,483,485,487,489,491,493,496,498,500,502,504,506,509,511,513,515,517],[149,149,149,384,151,149,151,151,149],4.466,[149,153,149,386,151,149,151,151,149],8.214,[149,156,149,388,151,149,151,151,149],19.348,[149,159,149,390,151,149,151,151,149],1.652,[149,201,149,392,151,149,151,151,149],3.166,[149,213,149,394,151,149,151,151,149],5.419,[153,149,149,396,151,149,151,151,149],3.59,[153,153,149,398,151,149,151,151,149],10.906,[153,156,149,400,151,149,151,151,149],18.869,[153,159,149,402,151,149,151,151,149],1.076,[153,201,149,404,151,149,151,151,149],1.768,[153,213,149,406,151,149,151,151,149],5.279,[156,149,149,408,151,149,151,151,149],4.178,[156,153,149,410,151,149,151,151,149],4.252,[156,156,149,412,151,149,151,151,149],10.618,[156,159,149,414,151,149,151,151,149],1.787,[156,201,149,416,151,149,151,151,149],2.398,[156,213,149,418,151,149,151,151,149],5.216,[159,149,149,420,151,149,151,151,149],2.208,[159,153,149,422,151,149,151,151,149],5.162,[159,156,149,424,151,149,151,151,149],10.693,[159,159,149,426,151,149,151,151,149],1.14,[159,201,149,428,151,149,151,151,149],2.31,[159,213,149,430,151,149,151,151,149],5.591,[201,149,149,432,151,149,151,151,149],27.139,[201,153,149,434,151,149,151,151,149],35.195,[201,156,149,436,151,149,151,151,149],44.235,[201,159,149,438,151,149,151,151,149],1.969,[201,201,149,440,151,149,151,151,149],3.674,[201,213,149,442,151,149,151,151,149],5.094,[213,149,149,444,151,149,151,151,149],5.477,[213,153,149,446,151,149,151,151,149],7.912,[213,156,149,448,151,149,151,151,149],13.7,[213,159,149,450,151,149,151,151,149],1.412,[213,201,149,452,151,149,151,151,149],2.032,[213,213,149,454,151,149,151,151,149],5.253,[104,149,149,456,151,149,151,151,149],1.673,[104,153,149,458,151,149,151,151,149],3.351,[104,156,149,460,151,149,151,151,149],5.669,[104,159,149,462,151,149,151,151,149],1.335,[104,201,149,464,151,149,151,151,149],1.983,[104,213,149,466,151,149,151,151,149],8.136,[468,149,149,469,151,149,151,151,149],7,0.424,[468,153,149,471,151,149,151,151,149],0.623,[468,156,149,473,151,149,151,151,149],1.473,[468,159,149,475,151,149,151,151,149],3.83,[468,201,149,477,151,149,151,151,149],6.554,[468,213,149,479,151,149,151,151,149],9.659,[481,149,149,482,151,149,151,151,149],8,34.865,[481,153,149,484,151,149,151,151,149],43.069,[481,156,149,486,151,149,151,151,149],44.88,[481,159,149,488,151,149,151,151,149],1.945,[481,201,149,490,151,149,151,151,149],2.667,[481,213,149,492,151,149,151,151,149],9.945,[494,149,149,495,151,149,151,151,149],9,11.741,[494,153,149,497,151,149,151,151,149],21.618,[494,156,149,499,151,149,151,151,149],40.482,[494,159,149,501,151,149,151,151,149],5.007,[494,201,149,503,151,149,151,151,149],6.566,[494,213,149,505,151,149,151,151,149],9.231,[507,149,149,508,151,149,151,151,149],10,0.272,[507,153,149,510,151,149,151,151,149],0.329,[507,156,149,512,151,149,151,151,149],0.409,[507,159,149,514,151,149,151,151,149],0.053,[507,201,149,516,151,149,151,151,149],0.148,[507,213,149,518,151,149,151,151,149],0.352,[],[338],[],[],[524],"Coarse registration on 250 samples (50 per model) with random rigid perturbations (roll and pitch within 30 deg, yaw within 180 deg, translation within 10 m); only successful results with RE \u003C 45 deg and TE \u003C 10 m are included; A50, A75 and A95 quantiles of rotation and translation error against the benchmark alignment",{"slug":526,"group":527,"sourceId":5,"sourceLabel":6,"table":528,"selfRows":104,"metrics":529,"seqs":543,"entrants":546,"cells":555,"outcomes":592,"locators":593,"hardware":594,"wordings":595,"notes":596},"zhang2024globalbimreg-table-2","zhang2024globalbimreg:Table 2","Table 2",[530,532,535,537,539,541],{"label":531,"unit":114,"statistic":252,"alignment":115},"Time [s], computation time per registration",{"label":533,"unit":91,"statistic":534,"alignment":115},"RMSE (BIM-point deviation; unit not stated)","RMSE",{"label":536,"unit":123,"statistic":342,"alignment":115},"TE-median, translation error",{"label":538,"unit":120,"statistic":342,"alignment":115},"RE-median, rotation error",{"label":540,"unit":123,"statistic":252,"alignment":115},"TE-mean, translation error",{"label":542,"unit":120,"statistic":252,"alignment":115},"RE-mean, rotation error",[544],{"dataset":90,"sequence":545,"environment":258},"Models 01-05",[547,550,553],{"name":548,"methodId":549,"linkable":144,"proposed":69,"self":69},"ICP (point-to-point)","besl1992icp",{"name":551,"methodId":552,"linkable":144,"proposed":69,"self":69},"ICP (point-to-plane)","chen1992pointtoplane",{"name":554,"methodId":5,"linkable":144,"proposed":144,"self":144},"Ours (point-level fine registration with BIM-point association)",[556,558,560,562,564,566,568,570,572,574,576,578,580,582,584,586,588,590],[149,149,149,557,151,149,149,151,149],16.34,[149,153,149,559,151,149,151,151,149],0.0437,[149,156,149,561,151,149,151,151,149],0.0422,[149,159,149,563,151,149,151,151,149],0.1366,[149,201,149,565,151,149,151,151,149],0.0862,[149,213,149,567,151,149,151,151,149],0.1448,[153,149,149,569,151,149,149,151,149],12.12,[153,153,149,571,151,149,151,151,149],0.0445,[153,156,149,573,151,149,151,151,149],0.051,[153,159,149,575,151,149,151,151,149],0.1091,[153,201,149,577,151,149,151,151,149],0.0907,[153,213,149,579,151,149,151,151,149],0.1323,[156,149,149,581,151,149,149,151,149],16.57,[156,153,149,583,151,149,151,151,149],0.0404,[156,156,149,585,151,149,151,151,149],0.0246,[156,159,149,587,151,149,151,151,149],0.094,[156,201,149,589,151,149,151,151,149],0.0602,[156,213,149,591,151,149,151,151,149],0.1099,[],[528],[240],[],[597],"Fine registration after coarse alignment on the simulation samples; errors against the benchmark alignment",[599,605],{"group":600,"slug":601,"sourceLabel":602,"table":528,"selfRows":213,"datasets":603},"bimloc2026:Table 2","bimloc2026-table-2","Zhang et al., 2026",[604],"BIM-robot simulation benchmark (CityU-02)",{"group":606,"slug":607,"sourceLabel":6,"table":608,"selfRows":153,"datasets":609},"zhang2024globalbimreg:Text Sec.4.1.2","zhang2024globalbimreg-text-sec-4-1-2","Text Sec.4.1.2",[90],1790510658214]