[{"data":1,"prerenderedAt":612},["ShallowReactive",2],{"method-oleynikova2017voxblox":3},{"method":4,"reference":56,"equipment":77,"figures":130,"results":131},{"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":24,"limitations":29,"sensors":34,"platform":37,"estimator":40,"association":41,"timeModel":42,"deskew":43,"loopClosure":44,"globalOptimization":44,"mapRepresentation":45,"prior":46,"outputGeometry":47,"compute":48,"codeUrl":49,"codeLicense":50,"relatedVersions":51},"oleynikova2017voxblox","Oleynikova et al., 2017","Voxblox","Voxblox: Incremental 3D Euclidean Signed Distance Fields for on-board MAV planning",2017,"recent","C12","map_representation_or_reconstruction","Voxblox 以體素雜湊（voxel hashing）儲存 TSDF，並提出兩項整合策略：同一體素內的點先分組取加權平均再只射線投射一次（grouped raycasting），以及考量深度平方雜訊與表面後方線性衰減的權重函數。接著以波前傳播（raise\u002Flower wavefront）由 TSDF 增量建立歐氏有號距離場（ESDF）供無人機路徑規劃，並可隨時以 marching cubes 輸出網格。","Builds TSDFs with voxel hashing, grouped ray casting and a depth-dependent weighting with behind-surface drop-off, then incrementally derives an ESDF for planning and meshes on demand.","full_text_reviewed","peer_reviewed_published","main_body","未在營建場域驗證；TSDF 表面誤差以 Leica TPS MS50 雷射掃描所得結構真值評估（cow 資料集與 EuRoC V1_01），並報告誤差隨體素尺寸與權重函數而變。",[20,21,22,23],"public_benchmark","controlled_experiment","simulation","independent_reference",[25,26,27,28],"Grouped ray casting is up to 20 times faster than standard ray casting into a TSDF and up to 2 times faster than grouped OctoMap insertion (Sec. IV-B, Fig. 6).","Proposed quadratic weighting yields lower reconstruction RMS error than constant weighting, with a larger effect at larger voxel sizes (Sec. VI-A, Fig. 5).","In simulation every TSDF-derived ESDF variant had lower error than an ESDF built from occupancy, and a one-voxel fixed band gave the lowest error (Sec. VI-B1, Fig. 8).","Incremental ESDF updates were about an order of magnitude faster than batch updates on EuRoC (Sec. VI-B2, Fig. 9).",[30,31,32,33],"Quasi-Euclidean ESDF distances introduce error; authors recommend inflating robot bounding boxes by 8.25% (Sec. V-B).","Full Euclidean distance reduced ESDF error by 8.23\u002F5.18\u002F4.72% at 0.05\u002F0.10\u002F0.20 m voxels but increased integration time by 201.0\u002F61.3\u002F33.9% (Sec. VI-B).","nvblox authors state that voxblox is limited in achievable map resolution by CPU update cost (Millane et al. 2024, Sec. II).","The conclusion recommends a more conservative inflation of 8.5% + 0.3v (v = voxel size) to cover map errors (Sec. VIII); cite the section-specific value.",[35,36],"RGB-D","stereo",[38,39],"UAV (AscTec Firefly with forward stereo camera and IMU, on-board experiment; EuRoC MAV V1_01 dataset)","simulation (noiseless RGB-D, 320 x 240, Sec. VI-B1)","not_applicable (poses supplied externally, e.g., Vicon or visual-inertial pose)","grouped (merged) ray casting of points into TSDF voxels","not_applicable","not_reported","none","voxel-hashed TSDF layer, incremental ESDF layer, mesh layer","external poses","TSDF, ESDF and incremental marching-cubes mesh","single CPU thread; experiments on a quad-core i7 at 2.5 GHz using one thread; on the MAV an on-board Intel i7 at 2.1 GHz ran state estimation, TSDF integration, ESDF updates at 4 Hz with 0.20 m voxels and replanning within a 250 ms budget (Sec. VI, VII)","https:\u002F\u002Fgithub.com\u002Fethz-asl\u002Fvoxblox","BSD-3-Clause (repository LICENSE)",[52],{"relation":53,"title":54,"doi_or_url":55},"preprint","arXiv:1611.03631 (v1 2016-11-11, v2)","https:\u002F\u002Farxiv.org\u002Fabs\u002F1611.03631",{"id":5,"kind":57,"shortName":7,"title":8,"authors":58,"year":9,"venue":64,"venueType":65,"publisher":66,"volumeIssuePages":67,"doi":68,"arxivId":69,"url":55,"firstPublicDate":70,"publicationStatus":16,"metadataStatus":71,"fulltextStatus":15,"era":10,"classicReason":42,"codeUrl":49,"cluster":11,"topics":72,"mdpi":73,"verification":74,"label":6,"fulltextRoute":75,"versionRead":76,"addedByCensus":73},"method",[59,60,61,62,63],"Helen Oleynikova","Zachary Taylor","Marius Fehr","Roland Siegwart","Juan Nieto","2017 IEEE\u002FRSJ International Conference on Intelligent Robots and Systems (IROS)","conference","IEEE","pp. 1366-1373","10.1109\u002Firos.2017.8202315","1611.03631","2016-11-11","metadata_verified",[11],false,"corrected","NTU institutional (Chrome)","IEEE IROS 2017 version of record pp. 1366-1373 (read in full via NTU access) and arXiv v2 (2017-04-21, 'Submitted to IROS 2017', read in full)",[78,84,89,93,97,100,102,108,114,118,122,125],{"category":79,"model":80,"canonical":80,"role":81,"dataset":82,"specs":43,"locator":83},"rgbd","Microsoft Kinect (original)","dataset sensor","cow dataset","Sec. VI",{"category":85,"model":86,"canonical":86,"role":87,"dataset":82,"specs":88,"locator":83},"other","Vicon motion capture system","reference or ground truth","pose source for the cow dataset",{"category":90,"model":91,"canonical":91,"role":87,"dataset":82,"specs":92,"locator":83},"total_station","Leica TPS MS50","described as a laser scanner; 3 scans merged for structure ground truth",{"category":94,"model":95,"canonical":95,"role":81,"dataset":96,"specs":43,"locator":83},"stereo_camera","narrow-baseline grayscale stereo sensor (model not named)","EuRoC MAV (V1_01_easy)",{"category":85,"model":98,"canonical":98,"role":87,"dataset":96,"specs":99,"locator":83},"Vicon fused with IMU","pose information for EuRoC",{"category":90,"model":91,"canonical":91,"role":87,"dataset":96,"specs":101,"locator":83},"scans used as structure ground truth",{"category":103,"model":104,"canonical":104,"role":105,"dataset":106,"specs":107,"locator":83},"compute","quad-core Intel i7 2.5 GHz","compute for runtime",null,"one thread used",{"category":109,"model":110,"canonical":110,"role":111,"dataset":106,"specs":112,"locator":113},"platform","AscTec Firefly","method input","MAV; all estimation, mapping, planning and control on board","Sec. VII, Fig. 1",{"category":94,"model":115,"canonical":115,"role":111,"dataset":106,"specs":116,"locator":117},"forward-facing stereo camera synced to an IMU (model not named)","stereo matching input to mapping and to the visual-inertial estimator","Sec. VII",{"category":119,"model":120,"canonical":120,"role":111,"dataset":106,"specs":121,"locator":117},"imu","IMU synced to the stereo camera (model not named)","input to the visual-inertial state estimator",{"category":103,"model":123,"canonical":123,"role":105,"dataset":106,"specs":124,"locator":117},"Intel i7 2.1 GHz (on-board)","on-board MAV computer",{"category":85,"model":126,"canonical":126,"role":81,"dataset":127,"specs":128,"locator":129},"simulated noiseless RGB-D sensor","synthetic ESDF benchmark","320 x 240, maximum range 5 m, 50 random poses","Sec. VI-B1",[],{"totalRows":132,"groupCount":133,"groups":134,"others":555},96,14,[135,287,397,474],{"slug":136,"group":137,"sourceId":138,"sourceLabel":139,"table":140,"selfRows":141,"metrics":142,"seqs":155,"entrants":163,"cells":169,"outcomes":277,"locators":279,"hardware":280,"wordings":284,"notes":285},"millane2024nvblox-table-i","millane2024nvblox:Table I","millane2024nvblox","Millane et al., 2024","Table I",30,[143,147,149,151,153],{"label":144,"unit":145,"statistic":146,"alignment":42},"ESDF component runtime (ms), computed every 4 frames","ms","mean",{"label":148,"unit":145,"statistic":146,"alignment":42},"TSDF component runtime (ms)",{"label":150,"unit":145,"statistic":146,"alignment":42},"Color component runtime (ms)",{"label":152,"unit":145,"statistic":146,"alignment":42},"TSDF+Color component runtime (ms)",{"label":154,"unit":145,"statistic":146,"alignment":42},"Mesh component runtime (ms), computed every 4 frames",[156,160],{"dataset":157,"sequence":158,"environment":159},"Replica","average over sequences","synthetic rooms (photorealistic renderings)",{"dataset":161,"sequence":158,"environment":162},"Redwood","real consumer depth camera scans",[164,167],{"name":165,"methodId":138,"linkable":166,"proposed":166,"self":73},"nvblox",true,{"name":168,"methodId":5,"linkable":166,"proposed":73,"self":166},"voxblox",[170,174,177,179,181,184,186,188,189,191,192,194,195,197,198,200,201,203,204,207,209,211,213,215,217,219,221,222,224,226,228,230,232,234,236,237,239,241,242,243,244,246,247,249,250,251,252,254,255,257,259,261,263,265,267,268,270,271,273,275],[171,171,171,172,173,171,171,173,171],0,1.9,-1,[175,171,171,176,173,171,171,173,171],1,163.2,[171,171,171,178,173,171,175,173,171],3.6,[175,171,171,180,173,171,175,173,171],291.5,[171,171,171,182,173,171,183,173,171],8.4,2,[175,171,171,185,173,171,183,173,171],231.6,[171,175,171,187,173,171,171,173,171],0.4,[175,175,171,106,171,171,171,173,171],[171,175,171,190,173,171,175,173,171],0.6,[175,175,171,106,171,171,175,173,171],[171,175,171,193,173,171,183,173,171],1.6,[175,175,171,106,171,171,183,173,171],[171,183,171,196,173,171,171,173,171],1.7,[175,183,171,106,171,171,171,173,171],[171,183,171,199,173,171,175,173,171],2.5,[175,183,171,106,171,171,175,173,171],[171,183,171,202,173,171,183,173,171],4.2,[175,183,171,106,171,171,183,173,171],[171,205,171,206,173,171,171,173,171],3,2.1,[175,205,171,208,173,171,171,173,171],86.7,[171,205,171,210,173,171,175,173,171],3.2,[175,205,171,212,173,171,175,173,171],106.6,[171,205,171,214,173,171,183,173,171],5.8,[175,205,171,216,173,171,183,173,171],226.7,[171,218,171,193,173,171,171,173,171],4,[175,218,171,220,173,171,171,173,171],6.2,[171,218,171,218,173,171,175,173,171],[175,218,171,223,173,171,175,173,171],12,[171,218,171,225,173,171,183,173,171],12.3,[175,218,171,227,173,171,183,173,171],15.4,[171,171,175,229,173,171,171,173,171],1.5,[175,171,175,231,173,171,171,173,171],29.1,[171,171,175,233,173,171,175,173,171],2.6,[175,171,175,235,173,171,175,173,171],46.5,[171,171,175,202,173,171,183,173,171],[175,171,175,238,173,171,183,173,171],38.7,[171,175,175,240,173,171,171,173,171],0.2,[175,175,175,106,171,171,171,173,171],[171,175,175,240,173,171,175,173,171],[175,175,175,106,171,171,175,173,171],[171,175,175,245,173,171,183,173,171],0.5,[175,175,175,106,171,171,183,173,171],[171,183,175,248,173,171,171,173,171],1.1,[175,183,175,106,171,171,171,173,171],[171,183,175,193,173,171,175,173,171],[175,183,175,106,171,171,175,173,171],[171,183,175,253,173,171,183,173,171],2.4,[175,183,175,106,171,171,183,173,171],[171,205,175,256,173,171,171,173,171],1.3,[175,205,175,258,173,171,171,173,171],38.4,[171,205,175,260,173,171,175,173,171],1.8,[175,205,175,262,173,171,175,173,171],33.6,[171,205,175,264,173,171,183,173,171],2.9,[175,205,175,266,173,171,183,173,171],76.7,[171,218,175,190,173,171,171,173,171],[175,218,175,269,173,171,171,173,171],12.7,[171,218,175,229,173,171,175,173,171],[175,218,175,272,173,171,175,173,171],15.8,[171,218,175,274,173,171,183,173,171],2.7,[175,218,175,276,173,171,183,173,171],23,[278],"not_reported (voxblox does not separate TSDF and color integration)",[140],[281,282,283],"Desktop: Intel i9 CPU, NVIDIA RTX 3090 Ti","Laptop: Intel i7 CPU, RTX 3000 Mobile GPU","NVIDIA Jetson AGX Xavier",[],[286],"Component runtimes averaged over 8 Replica and 5 Redwood sequences at 5 cm voxels; ESDF and mesh computed every 4 frames; voxblox does not separate TSDF and color integration, so its TSDF and Color cells are empty; speed-up column not extracted",{"slug":288,"group":289,"sourceId":138,"sourceLabel":139,"table":290,"selfRows":133,"metrics":291,"seqs":301,"entrants":319,"cells":324,"outcomes":391,"locators":392,"hardware":393,"wordings":394,"notes":395},"millane2024nvblox-table-ii","millane2024nvblox:Table II","Table II",[292,296,298,300],{"label":293,"unit":294,"statistic":295,"alignment":42},"Median ESDF error (m)","m","median",{"label":297,"unit":145,"statistic":43,"alignment":42},"ESDF runtime (ms)",{"label":299,"unit":294,"statistic":146,"alignment":42},"Median ESDF error (m), Average row (arithmetic mean of the six per-sequence medians)",{"label":297,"unit":145,"statistic":146,"alignment":42},[302,305,307,309,311,313,316],{"dataset":161,"sequence":303,"environment":304},"apartment","indoor RGB-D scans",{"dataset":161,"sequence":306,"environment":304},"bedroom",{"dataset":161,"sequence":308,"environment":304},"boardroom",{"dataset":161,"sequence":310,"environment":304},"lobby",{"dataset":161,"sequence":312,"environment":304},"loft",{"dataset":314,"sequence":315,"environment":304},"Cow and lady","-",{"dataset":317,"sequence":318,"environment":304},"Average","all",[320,321,322],{"name":165,"methodId":138,"linkable":166,"proposed":166,"self":73},{"name":168,"methodId":5,"linkable":166,"proposed":73,"self":166},{"name":323,"methodId":106,"linkable":73,"proposed":73,"self":73},"Fiesta",[325,327,328,330,332,334,336,338,340,341,343,345,347,348,349,351,352,353,354,356,357,358,360,361,363,364,365,366,368,369,370,373,375,376,378,380,382,384,385,386,388,389],[171,171,171,326,173,171,173,173,171],0.04,[171,175,171,196,173,171,171,173,171],[175,171,171,329,173,171,173,173,171],0.06,[175,175,171,331,173,171,171,173,171],25,[183,171,171,333,173,171,173,173,171],0.05,[183,175,171,335,173,171,171,173,171],5.5,[171,171,175,337,173,171,173,173,171],0.02,[171,175,175,339,173,171,171,173,171],1.4,[175,171,175,333,173,171,173,173,171],[175,175,175,342,173,171,171,173,171],22,[183,171,175,344,173,171,173,173,171],0.03,[183,175,175,346,173,171,171,173,171],3.4,[171,171,183,329,173,171,173,173,171],[171,175,183,196,173,171,171,173,171],[175,171,183,350,173,171,173,173,171],0.08,[175,175,183,141,173,171,171,173,171],[183,171,183,329,173,171,173,173,171],[183,175,183,218,173,171,171,173,171],[171,171,205,355,173,171,173,173,171],0.1,[171,175,205,206,173,171,171,173,171],[175,171,205,355,173,171,173,173,171],[175,175,205,359,173,171,171,173,171],34,[183,171,205,350,173,171,173,173,171],[183,175,205,362,173,171,171,173,171],5.2,[171,171,218,326,173,171,173,173,171],[171,175,218,260,173,171,171,173,171],[175,171,218,350,173,171,173,173,171],[175,175,218,367,173,171,171,173,171],48,[183,171,218,326,173,171,173,173,171],[183,175,218,182,173,171,171,173,171],[171,171,371,372,173,171,173,173,171],5,0.09,[171,175,371,374,173,171,171,173,171],2.8,[175,171,371,329,173,171,173,173,171],[175,175,371,377,173,171,171,173,171],190,[183,171,371,379,173,171,173,173,171],0.07,[183,175,371,381,173,171,171,173,171],52,[171,183,383,329,173,171,173,173,171],6,[171,205,383,172,173,171,171,173,171],[175,183,383,379,173,171,173,173,171],[175,205,383,387,173,171,171,173,171],58,[183,183,383,329,173,171,173,173,171],[183,205,383,390,173,171,171,173,171],13,[],[290],[281],[],[396],"Incremental ESDF on the Desktop platform; error is the median absolute voxel-wise difference to a voxelized ESDF ground truth computed from reconstructed voxel centres to the dataset ground-truth surface; the table cites Redwood as [3] although the caption cites [32]",{"slug":398,"group":399,"sourceId":400,"sourceLabel":401,"table":290,"selfRows":402,"metrics":403,"seqs":410,"entrants":419,"cells":428,"outcomes":467,"locators":468,"hardware":469,"wordings":470,"notes":471},"cblox2018-table-ii","cblox2018:Table II","cblox2018","Millane et al., 2018",10,[404,407],{"label":405,"unit":294,"statistic":406,"alignment":43},"RMSE (m)","RMSE",{"label":408,"unit":409,"statistic":43,"alignment":43},"Size (blocks)","voxel blocks",[411,415,417],{"dataset":412,"sequence":413,"environment":414},"CARLA (simulated)","l0","simulated urban driving (CARLA)",{"dataset":412,"sequence":416,"environment":414},"l1",{"dataset":412,"sequence":418,"environment":414},"median of l0 and l1",[420,422,424,426],{"name":421,"methodId":5,"linkable":166,"proposed":73,"self":166},"Voxblox (GT Poses)",{"name":423,"methodId":5,"linkable":166,"proposed":73,"self":166},"Voxblox (ORB-SLAM Poses)",{"name":425,"methodId":400,"linkable":166,"proposed":73,"self":73},"Ours (subvolume fusion OFF, ablation)",{"name":427,"methodId":400,"linkable":166,"proposed":166,"self":73},"Ours (subvolume fusion ON)",[429,431,433,435,437,439,441,443,444,445,447,449,451,453,455,457,459,461,463,465],[171,171,171,430,173,171,173,173,171],0.52,[175,171,171,432,173,171,173,173,171],2.12,[183,171,171,434,173,171,173,173,171],0.59,[205,171,171,436,173,171,173,173,171],0.66,[171,171,175,438,173,171,173,173,171],0.7,[175,171,175,440,173,171,173,173,171],2.06,[183,171,175,442,173,171,173,173,171],0.77,[205,171,175,442,173,171,173,173,171],[171,171,183,190,173,171,173,173,171],[175,171,183,446,173,171,173,173,171],2.09,[183,171,183,448,173,171,173,173,171],0.68,[205,171,183,450,173,171,173,173,171],0.72,[171,175,171,452,173,171,173,173,175],6315,[175,175,171,454,173,171,173,173,175],7205,[183,175,171,456,173,171,173,173,175],28908,[205,175,171,458,173,171,173,173,175],15873,[171,175,175,460,173,171,173,173,175],4561,[175,175,175,462,173,171,173,173,175],5240,[183,175,175,464,173,171,173,173,175],17856,[205,175,175,466,173,171,173,173,175],12220,[],[290],[],[],[472,473],"CARLA simulated drives l0 and l1 through two synthetic cities; reference geometry is a voxblox reconstruction with ground-truth poses and 0.25 m voxels; evaluated systems use 0.5 m voxels; tracking and integration at 10 Hz; 'Voxblox (ORB-SLAM Poses)' has no dense-map correction after loop closure","CARLA simulated drives l0 and l1 through two synthetic cities; reference geometry is a voxblox reconstruction with ground-truth poses and 0.25 m voxels; evaluated systems use 0.5 m voxels; tracking and integration at 10 Hz; 'Voxblox (ORB-SLAM Poses)' has no dense-map correction after loop closure; map size as number of allocated voxel blocks",{"slug":475,"group":476,"sourceId":477,"sourceLabel":478,"table":479,"selfRows":480,"metrics":481,"seqs":487,"entrants":500,"cells":512,"outcomes":548,"locators":550,"hardware":551,"wordings":552,"notes":553},"vizzo2022vdbfusion-table-6","vizzo2022vdbfusion:Table 6","vizzo2022vdbfusion","Vizzo et al., 2022","Table 6",7,[482,484],{"label":483,"unit":294,"statistic":146,"alignment":43},"point-to-point distance to reference map, mean",{"label":485,"unit":294,"statistic":486,"alignment":43},"point-to-point distance to reference map, standard deviation","std",[488,492,494,498],{"dataset":489,"sequence":490,"environment":491},"KITTI Odometry","07 (without space carving)","urban driving",{"dataset":489,"sequence":493,"environment":491},"07 (with space carving)",{"dataset":495,"sequence":496,"environment":497},"Cow and Lady","Cow and Lady (without space carving)","indoor RGB-D scene",{"dataset":495,"sequence":499,"environment":497},"Cow and Lady (with space carving)",[501,503,505,508,510],{"name":502,"methodId":5,"linkable":166,"proposed":73,"self":166},"Voxblox (without space carving)",{"name":504,"methodId":477,"linkable":166,"proposed":166,"self":73},"VDBFusion (without space carving)",{"name":506,"methodId":507,"linkable":166,"proposed":73,"self":73},"Octomap (with space carving)","hornung2013octomap",{"name":509,"methodId":5,"linkable":166,"proposed":73,"self":166},"Voxblox (with space carving)",{"name":511,"methodId":477,"linkable":166,"proposed":166,"self":73},"VDBFusion (with space carving)",[513,514,516,518,520,522,524,526,528,530,532,534,536,538,540,542,544,546],[171,171,171,106,171,171,173,173,171],[175,171,171,515,173,171,173,173,171],0.031,[183,171,175,517,173,171,173,173,171],0.033,[183,175,175,519,173,171,173,173,171],0.035,[205,171,175,521,173,171,173,173,171],0.497,[205,175,175,523,173,171,173,173,171],1.991,[218,171,175,525,173,171,173,173,171],0.023,[218,175,175,527,173,171,173,173,171],0.022,[171,171,183,529,173,171,173,173,171],0.236,[171,175,183,531,173,171,173,173,171],0.298,[175,171,183,533,173,171,173,173,171],0.049,[175,175,183,535,173,171,173,173,171],0.065,[183,171,205,537,173,171,173,173,171],0.195,[183,175,205,539,173,171,173,173,171],0.262,[205,171,205,541,173,171,173,173,171],0.319,[205,175,205,543,173,171,173,173,171],0.398,[218,171,205,545,173,171,173,173,171],0.045,[218,175,205,547,173,171,173,173,171],0.062,[549],"failed",[479],[],[],[554],"Point-to-point distance (m) between densely sampled maps (KITTI 100,000,000 points, Cow and Lady 1,000,000 points) and the reference cloud; KITTI reference = all KITTI 07 scans aggregated without downsampling, dynamic objects removed with SemanticKITTI labels; Cow and Lady reference from a high-resolution scanner supplied with the dataset; Octomap evaluated through its own point-cloud export",[556,561,566,572,578,583,590,596,601,606],{"group":557,"slug":558,"sourceLabel":6,"table":559,"selfRows":383,"datasets":560},"oleynikova2017voxblox:Text Sec. VI-B1","oleynikova2017voxblox-text-sec-vi-b1","Text Sec. VI-B1",[127],{"group":562,"slug":563,"sourceLabel":401,"table":140,"selfRows":371,"datasets":564},"cblox2018:Table I","cblox2018-table-i",[565],"ICL-NUIM",{"group":567,"slug":568,"sourceLabel":569,"table":290,"selfRows":371,"datasets":570},"shinemapping2023:Table II","shinemapping2023-table-ii","Zhong et al., 2023",[571],"MaiCity (synthetic)",{"group":573,"slug":574,"sourceLabel":569,"table":575,"selfRows":371,"datasets":576},"shinemapping2023:Table III","shinemapping2023-table-iii","Table III",[577],"Newer College",{"group":579,"slug":580,"sourceLabel":478,"table":581,"selfRows":218,"datasets":582},"vizzo2022vdbfusion:Table 2","vizzo2022vdbfusion-table-2","Table 2",[495,489],{"group":584,"slug":585,"sourceLabel":586,"table":587,"selfRows":205,"datasets":588},"affan2026semanticmeshing:Table 1","affan2026semanticmeshing-table-1","Affan et al., 2026","Table 1",[589],"Oxford Spires",{"group":591,"slug":592,"sourceLabel":6,"table":593,"selfRows":183,"datasets":594},"oleynikova2017voxblox:Text Fig. 6 caption","oleynikova2017voxblox-text-fig-6-caption","Text Fig. 6 caption",[595],"EuRoC MAV",{"group":597,"slug":598,"sourceLabel":478,"table":599,"selfRows":183,"datasets":600},"vizzo2022vdbfusion:Table 4","vizzo2022vdbfusion-table-4","Table 4",[495,489],{"group":602,"slug":603,"sourceLabel":478,"table":604,"selfRows":183,"datasets":605},"vizzo2022vdbfusion:Table 5","vizzo2022vdbfusion-table-5","Table 5",[495,489],{"group":607,"slug":608,"sourceLabel":401,"table":609,"selfRows":175,"datasets":610},"cblox2018:Text Sec.V-C","cblox2018-text-sec-v-c","Text Sec.V-C",[611],"authors' MAV industrial flights",1790510662478]