[{"data":1,"prerenderedAt":589},["ShallowReactive",2],{"method-mast3rslam2025":3},{"method":4,"reference":55,"equipment":75,"figures":105,"results":106},{"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":21,"limitations":27,"sensors":35,"platform":37,"estimator":38,"association":39,"timeModel":40,"deskew":41,"loopClosure":42,"globalOptimization":43,"mapRepresentation":44,"prior":45,"outputGeometry":46,"compute":47,"codeUrl":48,"codeLicense":49,"relatedVersions":50},"mast3rslam2025","Murai et al., 2025","MASt3R-SLAM","MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors",2025,"recent","C09","full_slam_with_global_correction","MASt3R-SLAM 以 MASt3R 雙視角重建先驗為核心建構即時單目稠密 SLAM，只假設單一相機中心，用迭代投影做點圖匹配、以 Sim(3) 位姿處理預測間不一致的尺度，並以影像檢索做迴圈閉合與重定位，後端為二階全域最佳化。幾何評估在 EuRoC Vicon 房間以軌跡對齊結構掃描真值，在 7-Scenes 以 ICP 對齊深度反投影參考，並報告 RMSE。作者承認全域最佳化不精修幾何，且畸變大的相機會降低預測品質。","Real-time monocular dense SLAM built on MASt3R priors with Sim(3) poses, ray-error optimization, retrieval-based loop closure and dense pointmap fusion.","full_text_reviewed","peer_reviewed_published","main_body","論文未涉及營建場域；資料為 TUM RGB-D、7-Scenes、ETH3D-SLAM、EuRoC。",[20],"public_benchmark",[22,23,24,25,26],"Lower Chamfer and accuracy RMSE than DROID-SLAM on EuRoC Vicon rooms (Chamfer 0.085 vs 0.117 m) and 7-Scenes seq-01 (0.066 vs 0.077 m); DROID-SLAM has lower ATE on EuRoC (0.022 vs 0.041 m) and better completion, whereas on 7-Scenes the calibrated ATE is similar (0.047 vs 0.049 m) (Sec. 4.2; Table 3)","Works without known calibration (abstract)","TUM RGB-D calibrated average ATE 0.030 m, lowest in Table 1; uncalibrated 0.060 m vs 0.158 m for DROID-SLAM with GeoCalib intrinsics (Table 1)","ETH3D-SLAM train: lowest mean ATE (0.086 m) and highest AUC (23.935) among the monocular systems run (Fig. 5)","Projective pointmap matching takes about 2 ms versus 2000 ms for MASt3R matching over all pixels (Table 4)",[28,29,30,31,32,33,34],"Geometry not refined in the global optimization (Sec. 5)","Predictions degrade with lens distortion; trained on pinhole images (Sec. 5)","Full-resolution decoder is a throughput bottleneck (Sec. 5)","EuRoC average ATE 0.041 m is worse than DROID-SLAM and DPV-SLAM-based systems (0.022 to 0.024 m); authors note DROID-SLAM trains with greyscale augmentation (Sec. 4.1, Table 9)","Uncalibrated EuRoC runs required undistorted images because MASt3R had not been trained on such distortion (Sec. 4.1)","ETH3D evaluated only on train sequences because the official thresholds are too strict for monocular methods (Sec. 4.1)","Without loop closure EuRoC Vicon ATE rises from 0.029 to 0.233 m, showing drift from biased MASt3R outputs (Table 7)",[36],"monocular camera (uncalibrated, generic central camera)",[],"Gauss-Newton second-order optimization of Sim(3) keyframe poses minimizing ray error; sparse Cholesky backend in CUDA","MASt3R pointmap matching via iterative projective ray search","discrete poses","not_applicable","incremental ASMK image retrieval + MASt3R decoder matching; relocalisation via retrieval","second-order global optimization over the keyframe graph (first 7-DoF pose fixed)","per-keyframe canonical pointmaps with local fusion","MASt3R learned two-view 3D reconstruction prior","dense point cloud from fused pointmaps + trajectory (scale via Sim(3), not guaranteed metric)","Intel Core i9-12900K 3.50 GHz + NVIDIA GeForce RTX 4090; single-threaded system at about 15 FPS, so datasets were subsampled every 2 frames to simulate real time (not for ETH3D); average per-frame tracking 45.9 ms, per-keyframe backend 164.9 ms, 14.6 FPS; MASt3R encoder and decoder take about 64% of runtime; MASt3R outputs resized to 512 px on the largest side (Sec. 4, Supp. Sec. 10, Table 8)","https:\u002F\u002Fgithub.com\u002Frmurai0610\u002FMASt3R-SLAM","CC BY-NC-SA 4.0",[51],{"relation":52,"title":53,"doi_or_url":54},"preprint","arXiv:2412.12392","https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.12392",{"id":5,"kind":56,"shortName":7,"title":8,"authors":57,"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":41,"codeUrl":48,"cluster":11,"topics":70,"mdpi":71,"verification":72,"label":6,"fulltextRoute":73,"versionRead":74,"addedByCensus":71},"method",[58,59,60],"Riku Murai","Eric Dexheimer","Andrew J. Davison","2025 IEEE\u002FCVF Conference on Computer Vision and Pattern Recognition (CVPR)","conference","IEEE","pp. 16695-16705","10.1109\u002Fcvpr52734.2025.01556","2412.12392","https:\u002F\u002Fapi.crossref.org\u002Fworks\u002F10.1109\u002Fcvpr52734.2025.01556","2024-12-16","metadata_verified",[11],false,"corrected","arXiv","arXiv v2 (2025-06-02) including supplementary Sec. 8-13; main-paper key values (15 FPS, TUM average 0.030, EuRoC 0.041, Chamfer 0.085 and 0.066, i9-12900K + RTX 4090) cross-checked against the CVF open-access accepted version",[76,83,86,93,98],{"category":77,"model":78,"canonical":78,"role":79,"dataset":80,"specs":81,"locator":82},"compute","Intel Core i9 12900K 3.50GHz","compute for runtime",null,"desktop CPU","Sec. 4",{"category":77,"model":84,"canonical":84,"role":79,"dataset":80,"specs":85,"locator":82},"NVIDIA GeForce RTX 4090","single GPU",{"category":87,"model":88,"canonical":88,"role":89,"dataset":90,"specs":91,"locator":92},"rgbd","depth camera (model not named)","reference or ground truth","7-Scenes","depth images back-projected with dataset poses to form the reference cloud; default factory intrinsics","Sec. 4.2",{"category":94,"model":95,"canonical":95,"role":89,"dataset":96,"specs":97,"locator":92},"other","Vicon","EuRoC","Vicon trajectory; the estimated trajectory is aligned to it to place the estimated cloud in the frame of the EuRoC 3D structure-scan ground truth",{"category":99,"model":100,"canonical":100,"role":101,"dataset":102,"specs":103,"locator":104},"camera","monocular RGB camera (model not named)","method input","TUM RGB-D; 7-Scenes; ETH3D-SLAM; EuRoC","monocular RGB input with no parametric camera model assumed beyond a unique camera centre; EuRoC images undistorted for the uncalibrated run","Abstract; Sec. 3.1; Sec. 4; Sec. 4.1",[],{"totalRows":107,"groupCount":108,"groups":109,"others":563},78,9,[110,227,319,431],{"slug":111,"group":112,"sourceId":5,"sourceLabel":6,"table":113,"selfRows":114,"metrics":115,"seqs":121,"entrants":139,"cells":150,"outcomes":221,"locators":222,"hardware":223,"wordings":224,"notes":225},"mast3rslam2025-table-2","mast3rslam2025:Table 2","Table 2",16,[116],{"label":117,"unit":118,"statistic":119,"alignment":120},"ATE (m)","m","RMSE","Sim3",[122,125,127,129,131,133,135,137],{"dataset":90,"sequence":123,"environment":124},"chess","7-Scenes sequences as used by NICER-SLAM (chess, fire, heads, office, pumpkin, kitchen, stairs), monocular RGB, every 2nd frame",{"dataset":90,"sequence":126,"environment":124},"fire",{"dataset":90,"sequence":128,"environment":124},"heads",{"dataset":90,"sequence":130,"environment":124},"office",{"dataset":90,"sequence":132,"environment":124},"pumpkin",{"dataset":90,"sequence":134,"environment":124},"kitchen",{"dataset":90,"sequence":136,"environment":124},"stairs",{"dataset":90,"sequence":138,"environment":124},"avg",[140,142,146,148],{"name":141,"methodId":80,"linkable":71,"proposed":71,"self":71},"NICER-SLAM",{"name":143,"methodId":144,"linkable":145,"proposed":71,"self":71},"DROID-SLAM","droidslam2021",true,{"name":147,"methodId":5,"linkable":145,"proposed":145,"self":145},"MASt3R-SLAM (Ours, calibrated)",{"name":149,"methodId":5,"linkable":145,"proposed":145,"self":145},"MASt3R-SLAM (Ours*, uncalibrated)",[151,155,158,161,164,167,170,172,175,177,179,181,183,185,187,189,191,193,194,196,198,200,202,204,206,208,210,212,214,216,218,220],[152,152,152,153,154,152,154,154,152],0,0.033,-1,[152,152,156,157,154,152,154,154,152],1,0.069,[152,152,159,160,154,152,154,154,152],2,0.042,[152,152,162,163,154,152,154,154,152],3,0.108,[152,152,165,166,154,152,154,154,152],4,0.2,[152,152,168,169,154,152,154,154,152],5,0.039,[152,152,171,163,154,152,154,154,152],6,[152,152,173,174,154,152,154,154,152],7,0.086,[156,152,152,176,154,152,154,154,152],0.036,[156,152,156,178,154,152,154,154,152],0.027,[156,152,159,180,154,152,154,154,152],0.025,[156,152,162,182,154,152,154,154,152],0.066,[156,152,165,184,154,152,154,154,152],0.127,[156,152,168,186,154,152,154,154,152],0.04,[156,152,171,188,154,152,154,154,152],0.026,[156,152,173,190,154,152,154,154,152],0.049,[159,152,152,192,154,152,154,154,152],0.053,[159,152,156,180,154,152,154,154,152],[159,152,159,195,154,152,154,154,152],0.015,[159,152,162,197,154,152,154,154,152],0.097,[159,152,165,199,154,152,154,154,152],0.088,[159,152,168,201,154,152,154,154,152],0.041,[159,152,171,203,154,152,154,154,152],0.011,[159,152,173,205,154,152,154,154,152],0.047,[162,152,152,207,154,152,154,154,152],0.063,[162,152,156,209,154,152,154,154,152],0.046,[162,152,159,211,154,152,154,154,152],0.029,[162,152,162,213,154,152,154,154,152],0.103,[162,152,165,215,154,152,154,154,152],0.114,[162,152,168,217,154,152,154,154,152],0.074,[162,152,171,219,154,152,154,154,152],0.032,[162,152,173,182,154,152,154,154,152],[],[113],[],[],[226],"ATE RMSE (m) on 7-Scenes, monocular RGB, scaled trajectory alignment; sequences follow NICER-SLAM; NICER-SLAM values reported from NICER-SLAM; frames subsampled every 2 to simulate real time.",{"slug":228,"group":229,"sourceId":5,"sourceLabel":6,"table":230,"selfRows":114,"metrics":231,"seqs":244,"entrants":251,"cells":259,"outcomes":312,"locators":314,"hardware":315,"wordings":316,"notes":317},"mast3rslam2025-table-3","mast3rslam2025:Table 3","Table 3",[232,234,237,239,241,242,243],{"label":233,"unit":118,"statistic":119,"alignment":120},"ATE",{"label":235,"unit":118,"statistic":119,"alignment":236},"Accuracy (RMSE)","not_reported",{"label":238,"unit":118,"statistic":119,"alignment":236},"Completion (RMSE)",{"label":240,"unit":118,"statistic":119,"alignment":236},"Chamfer (average of accuracy and completion RMSE)",{"label":235,"unit":118,"statistic":119,"alignment":120},{"label":238,"unit":118,"statistic":119,"alignment":120},{"label":240,"unit":118,"statistic":119,"alignment":120},[245,248],{"dataset":90,"sequence":246,"environment":247},"seq-01 of each scene","7-Scenes seq-01 of each scene, monocular RGB input; reference cloud back-projected from the dataset depth camera images",{"dataset":96,"sequence":249,"environment":250},"Vicon room sequences (geometry); ATE see note","EuRoC Vicon room sequences for geometry, monocular input; the ATE column equals the 11-sequence average of Table 9",[252,253,255,257,258],{"name":143,"methodId":144,"linkable":145,"proposed":71,"self":71},{"name":254,"methodId":80,"linkable":71,"proposed":71,"self":71},"Spann3R @20",{"name":256,"methodId":80,"linkable":71,"proposed":71,"self":71},"Spann3R @2",{"name":147,"methodId":5,"linkable":145,"proposed":145,"self":145},{"name":149,"methodId":5,"linkable":145,"proposed":145,"self":145},[260,261,263,264,266,267,268,269,271,272,274,276,278,279,280,282,283,284,286,288,290,292,294,296,298,299,301,303,305,307,308,310],[152,152,152,190,154,152,154,154,152],[152,156,152,262,154,152,154,154,152],0.115,[152,159,152,186,154,152,154,154,152],[152,162,152,265,154,152,154,154,152],0.077,[156,152,152,80,152,152,154,154,152],[156,156,152,157,154,152,154,154,152],[156,159,152,205,154,152,154,154,152],[156,162,152,270,154,152,154,154,152],0.058,[159,152,152,80,152,152,154,154,152],[159,156,152,273,154,152,154,154,152],0.124,[159,159,152,275,154,152,154,154,152],0.043,[159,162,152,277,154,152,154,154,152],0.084,[162,152,152,205,154,152,154,154,152],[162,156,152,217,154,152,154,154,152],[162,159,152,281,154,152,154,154,152],0.057,[162,162,152,182,154,152,154,154,152],[165,152,152,182,154,152,154,154,152],[165,156,152,285,154,152,154,154,152],0.068,[165,159,152,287,154,152,154,154,152],0.045,[165,162,152,289,154,152,154,154,152],0.056,[152,152,156,291,154,152,154,154,152],0.022,[152,165,156,293,154,152,154,154,152],0.173,[152,168,156,295,154,152,154,154,152],0.061,[152,171,156,297,154,152,154,154,152],0.117,[162,152,156,201,154,152,154,154,152],[162,165,156,300,154,152,154,154,152],0.099,[162,168,156,302,154,152,154,154,152],0.071,[162,171,156,304,154,152,154,154,152],0.085,[165,152,156,306,154,152,154,154,152],0.164,[165,165,156,163,154,152,154,154,152],[165,168,156,309,154,152,154,154,152],0.072,[165,171,156,311,154,152,154,154,152],0.09,[313],"not_applicable (N\u002FA)",[230],[],[],[318],"Reconstruction evaluation (m). Accuracy and completion are RMSE of nearest-neighbour distances with a 0.5 m maximum distance, Chamfer is their average; no estimated points filtered; unobservable reference points removed. 7-Scenes uses seq-01 of each scene with a reference cloud back-projected from depth images and aligned to the estimate by ICP (scale handling not stated); EuRoC geometry uses the Vicon room sequences with the estimate aligned via its trajectory to Vicon (scaled alignment). Ours* = without known calibration; Spann3R keyframe every 20 or 2 images; Spann3R excluded on EuRoC. (reviewer inference) The EuRoC ATE column equals the 11-sequence averages of Table 9 (0.022, 0.041, 0.164), not a Vicon-only average.",{"slug":320,"group":321,"sourceId":322,"sourceLabel":323,"table":324,"selfRows":114,"metrics":325,"seqs":328,"entrants":339,"cells":351,"outcomes":422,"locators":423,"hardware":424,"wordings":425,"notes":426},"vggtslam2025-table-1","vggtslam2025:Table 1","vggtslam2025","Maggio et al., 2025","Table 1",[326],{"label":327,"unit":118,"statistic":119,"alignment":236},"ATE RMSE [m]",[329,331,332,333,334,335,336,337],{"dataset":90,"sequence":123,"environment":330},"not described in the paper",{"dataset":90,"sequence":126,"environment":330},{"dataset":90,"sequence":128,"environment":330},{"dataset":90,"sequence":130,"environment":330},{"dataset":90,"sequence":132,"environment":330},{"dataset":90,"sequence":134,"environment":330},{"dataset":90,"sequence":136,"environment":330},{"dataset":90,"sequence":338,"environment":330},"Avg",[340,341,342,343,345,347,349],{"name":141,"methodId":80,"linkable":71,"proposed":71,"self":71},{"name":143,"methodId":144,"linkable":145,"proposed":71,"self":71},{"name":7,"methodId":5,"linkable":145,"proposed":71,"self":145},{"name":344,"methodId":144,"linkable":145,"proposed":71,"self":71},"DROID-SLAM*",{"name":346,"methodId":5,"linkable":145,"proposed":71,"self":145},"MASt3R-SLAM*",{"name":348,"methodId":80,"linkable":71,"proposed":71,"self":71},"Ours (Sim(3), w = 32)",{"name":350,"methodId":322,"linkable":145,"proposed":145,"self":71},"Ours (SL(4), w = 32)",[352,353,354,355,356,357,358,359,360,361,362,363,364,365,366,367,368,369,370,371,372,373,374,375,376,377,379,381,383,385,387,389,391,392,393,394,395,396,397,398,399,401,402,404,406,408,409,411,413,414,416,417,418,419,420,421],[152,152,152,153,154,152,154,154,152],[152,152,156,157,154,152,154,154,152],[152,152,159,160,154,152,154,154,152],[152,152,162,163,154,152,154,154,152],[152,152,165,166,154,152,154,154,152],[152,152,168,169,154,152,154,154,152],[152,152,171,163,154,152,154,154,152],[152,152,173,174,154,152,154,154,152],[156,152,152,176,154,152,154,154,152],[156,152,156,178,154,152,154,154,152],[156,152,159,180,154,152,154,154,152],[156,152,162,182,154,152,154,154,152],[156,152,165,184,154,152,154,154,152],[156,152,168,186,154,152,154,154,152],[156,152,171,188,154,152,154,154,152],[156,152,173,190,154,152,154,154,152],[159,152,152,192,154,152,154,154,152],[159,152,156,180,154,152,154,154,152],[159,152,159,195,154,152,154,154,152],[159,152,162,197,154,152,154,154,152],[159,152,165,199,154,152,154,154,152],[159,152,168,201,154,152,154,154,152],[159,152,171,203,154,152,154,154,152],[159,152,173,205,154,152,154,154,152],[162,152,152,205,154,152,154,154,156],[162,152,156,378,154,152,154,154,156],0.038,[162,152,159,380,154,152,154,154,156],0.034,[162,152,162,382,154,152,154,154,156],0.136,[162,152,165,384,154,152,154,154,156],0.166,[162,152,168,386,154,152,154,154,156],0.08,[162,152,171,388,154,152,154,154,156],0.044,[162,152,173,390,154,152,154,154,156],0.078,[165,152,152,207,154,152,154,154,159],[165,152,156,209,154,152,154,154,159],[165,152,159,211,154,152,154,154,159],[165,152,162,213,154,152,154,154,159],[165,152,165,215,154,152,154,154,159],[165,152,168,217,154,152,154,154,159],[165,152,171,219,154,152,154,154,159],[165,152,173,182,154,152,154,154,159],[168,152,152,400,154,152,154,154,162],0.037,[168,152,156,188,154,152,154,154,162],[168,152,159,403,154,152,154,154,162],0.018,[168,152,162,405,154,152,154,154,162],0.104,[168,152,165,407,154,152,154,154,162],0.133,[168,152,168,295,154,152,154,154,162],[168,152,171,410,154,152,154,154,162],0.093,[168,152,173,412,154,152,154,154,162],0.067,[171,152,152,176,154,152,154,154,162],[171,152,156,415,154,152,154,154,162],0.028,[171,152,159,403,154,152,154,154,162],[171,152,162,213,154,152,154,154,162],[171,152,165,407,154,152,154,154,162],[171,152,168,270,154,152,154,154,162],[171,152,171,410,154,152,154,154,162],[171,152,173,412,154,152,154,154,162],[],[324],[],[],[427,428,429,430],"ATE RMSE on 7-Scenes computed with evo (alignment not stated); calibrated intrinsics; value reported from MASt3R-SLAM","ATE RMSE on 7-Scenes computed with evo (alignment not stated); uncalibrated; DROID-SLAM* intrinsics from an automatic calibration pipeline, run by the authors","ATE RMSE on 7-Scenes computed with evo (alignment not stated); uncalibrated; value reported from MASt3R-SLAM","ATE RMSE on 7-Scenes computed with evo (alignment not stated); uncalibrated; VGGT-SLAM average of five runs",{"slug":432,"group":433,"sourceId":322,"sourceLabel":323,"table":113,"selfRows":434,"metrics":435,"seqs":439,"entrants":460,"cells":480,"outcomes":555,"locators":557,"hardware":558,"wordings":559,"notes":560},"vggtslam2025-table-2","vggtslam2025:Table 2",11,[436,437],{"label":327,"unit":118,"statistic":119,"alignment":236},{"label":438,"unit":118,"statistic":119,"alignment":236},"ATE RMSE [m], average over 9 sequences",[440,443,445,447,449,451,453,455,457,459],{"dataset":441,"sequence":442,"environment":330},"TUM RGB-D","360",{"dataset":441,"sequence":444,"environment":330},"desk",{"dataset":441,"sequence":446,"environment":330},"desk2",{"dataset":441,"sequence":448,"environment":330},"floor",{"dataset":441,"sequence":450,"environment":330},"plant",{"dataset":441,"sequence":452,"environment":330},"room",{"dataset":441,"sequence":454,"environment":330},"rpy",{"dataset":441,"sequence":456,"environment":330},"teddy",{"dataset":441,"sequence":458,"environment":330},"xyz",{"dataset":441,"sequence":338,"environment":330},[461,462,463,464,465,468,470,472,474,476,478,479],{"name":344,"methodId":144,"linkable":145,"proposed":71,"self":71},{"name":346,"methodId":5,"linkable":145,"proposed":71,"self":145},{"name":348,"methodId":80,"linkable":71,"proposed":71,"self":71},{"name":350,"methodId":322,"linkable":145,"proposed":145,"self":71},{"name":466,"methodId":467,"linkable":145,"proposed":71,"self":71},"ORB-SLAM3","orbslam3_2021",{"name":469,"methodId":80,"linkable":71,"proposed":71,"self":71},"DeepV2D",{"name":471,"methodId":80,"linkable":71,"proposed":71,"self":71},"DeepFactors",{"name":473,"methodId":80,"linkable":71,"proposed":71,"self":71},"DPV-SLAM",{"name":475,"methodId":80,"linkable":71,"proposed":71,"self":71},"DPV-SLAM++",{"name":477,"methodId":80,"linkable":71,"proposed":71,"self":71},"GO-SLAM",{"name":143,"methodId":144,"linkable":145,"proposed":71,"self":71},{"name":7,"methodId":5,"linkable":145,"proposed":71,"self":145},[481,483,484,486,488,489,491,492,493,496,498,500,502,504,505,506,508,509,510,512,514,516,517,518,520,521,522,523,524,526,527,528,529,530,532,534,536,538,539,541,542,543,545,547,549,551,552,554],[152,152,152,482,154,152,154,154,152],0.202,[152,152,156,219,154,152,154,154,152],[152,152,159,485,154,152,154,154,152],0.091,[152,152,162,487,154,152,154,154,152],0.064,[152,152,165,287,154,152,154,154,152],[152,152,168,490,154,152,154,154,152],0.918,[152,152,171,289,154,152,154,154,152],[152,152,173,287,154,152,154,154,152],[152,152,494,495,154,152,154,154,152],8,0.012,[152,152,108,497,154,152,154,154,152],0.158,[156,152,152,499,154,152,154,154,152],0.07,[156,152,156,501,154,152,154,154,152],0.035,[156,152,159,503,154,152,154,154,152],0.055,[156,152,162,289,154,152,154,154,152],[156,152,165,501,154,152,154,154,152],[156,152,168,507,154,152,154,154,152],0.118,[156,152,171,201,154,152,154,154,152],[156,152,173,215,154,152,154,154,152],[156,152,494,511,154,152,154,154,152],0.02,[156,152,108,513,154,152,154,154,152],0.06,[159,152,152,515,154,152,154,154,152],0.123,[159,152,156,186,154,152,154,154,152],[159,152,159,503,154,152,154,154,152],[159,152,162,519,154,152,154,154,152],0.254,[159,152,165,291,154,152,154,154,152],[159,152,168,199,154,152,154,154,152],[159,152,171,201,154,152,154,154,152],[159,152,173,219,154,152,154,154,152],[159,152,494,525,154,152,154,154,152],0.016,[159,152,108,217,154,152,154,154,152],[162,152,152,302,154,152,154,154,152],[162,152,156,180,154,152,154,154,152],[162,152,159,186,154,152,154,154,152],[162,152,162,531,154,152,154,154,152],0.141,[162,152,165,533,154,152,154,154,152],0.023,[162,152,168,535,154,152,154,154,152],0.102,[162,152,171,537,154,152,154,154,152],0.03,[162,152,173,380,154,152,154,154,152],[162,152,494,540,154,152,154,154,152],0.014,[162,152,108,192,154,152,154,154,152],[165,156,108,80,152,152,154,154,156],[168,156,108,544,154,152,154,154,156],0.375,[171,156,108,546,154,152,154,154,156],0.233,[173,156,108,548,154,152,154,154,156],0.076,[494,156,108,550,154,152,154,154,156],0.054,[108,156,108,501,154,152,154,154,156],[553,156,108,378,154,152,154,154,156],10,[434,156,108,537,154,152,154,154,156],[556],"not_applicable (average reported as N\u002FA; cells for 360, floor, room, rpy and teddy marked x without explanation in the paper)",[113],[],[],[561,562],"ATE RMSE on TUM RGB-D (RGB only) computed with evo (alignment not stated); uncalibrated rows; floor sequence degenerate for SL(4) homography","ATE RMSE on TUM RGB-D; calibrated baselines with values reported from MASt3R-SLAM; only the average column extracted (row cap)",[564,568,572,578,584],{"group":565,"slug":566,"sourceLabel":323,"table":230,"selfRows":494,"datasets":567},"vggtslam2025:Table 3","vggtslam2025-table-3",[90],{"group":569,"slug":570,"sourceLabel":6,"table":324,"selfRows":165,"datasets":571},"mast3rslam2025:Table 1","mast3rslam2025-table-1",[441],{"group":573,"slug":574,"sourceLabel":6,"table":575,"selfRows":162,"datasets":576},"mast3rslam2025:Table 8","mast3rslam2025-table-8","Table 8",[577],"TUM RGB-D, 7-Scenes, EuRoC",{"group":579,"slug":580,"sourceLabel":6,"table":581,"selfRows":159,"datasets":582},"mast3rslam2025:Fig. 5 table","mast3rslam2025-fig-5-table","Fig. 5 table",[583],"ETH3D-SLAM",{"group":585,"slug":586,"sourceLabel":6,"table":587,"selfRows":159,"datasets":588},"mast3rslam2025:Table 9","mast3rslam2025-table-9","Table 9",[96],1790510665349]