[{"data":1,"prerenderedAt":539},["ShallowReactive",2],{"method-vggtslam2025":3},{"method":4,"reference":59,"equipment":79,"figures":93,"results":133},{"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},"vggtslam2025","Maggio et al., 2025","VGGT-SLAM","VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold",2025,"recent","C09","full_slam_with_global_correction","VGGT-SLAM 將 VGGT 產生的子地圖逐步對齊，指出在未校正相機下重建只確定到 15 自由度的射影變換，因此以 SL(4) 流形上的單應矩陣取代相似變換對齊子地圖，並加入以 SALAD 檢索的迴圈約束。作者明言重建不具公制尺度，影像須先去除鏡頭畸變，且當多張影像只看到單一平面（TUM 僅拍地板的片段）時單應估計會退化並使重建發散。NeurIPS 正式版補充的焦距統計顯示，VGGT 在同一場景內估計的焦距會明顯波動（桌面與路樁場景標準差 37.1 與 51.8 像素），這正是 SL(4) 明顯優於 Sim(3) 的情境；但在 7-Scenes 與 TUM 等一般場景，Sim(3) 版本表現相近，附錄中 w = 8 的 Sim(3) 版本在 TUM 平均 ATE 甚至更低（0.040 m 對 0.053 m）。每個子地圖的 VGGT 推論約 662 ms，SL(4) 對齊只多約 17 ms。建築室內若出現只拍到大面樓板或牆面的連續影格，可能觸發同類退化，需以實測驗證（推論）。","Aligns VGGT submaps with 15-DoF homographies on SL(4) plus loop closures to handle projective ambiguity of uncalibrated reconstruction.","full_text_reviewed","peer_reviewed_published","main_body","論文未涉及營建場域。作者觀察到當多張影像只看到平坦地板時，15 自由度單應估計出現非唯一解並使重建發散；建築室內若有只拍到大面樓板或牆面的連續影格，可能觸發同類退化，需另行驗證（推論）。",[20],"public_benchmark",[22,23,24,25,26],"Best accuracy and Chamfer RMSE on 7-Scenes dense evaluation following the MASt3R-SLAM protocol, by a small margin (Chamfer 0.055 m vs 0.056 m for uncalibrated MASt3R-SLAM); baseline values in this table differ from those reported in [mast3rslam2025] Table 3 (Sec. 5.3; Table 3)","Handles long videos infeasible for VGGT alone (abstract)","SL(4) alignment costs only about 17 ms more per submap than Sim(3), about 2.5% of VGGT inference time; back-end optimization about 0.5 ms (Sec. 5.4; Table 4)","VGGT focal-length estimates vary within a scene (std 37.1 and 51.8 px in the tabletop and bollards scenes versus 7.3 and 9.0 px in office loop and 7-Scenes), matching where SL(4) clearly beats Sim(3) (Appendix B.3; Table 10)","Qualitative 55 m office-corridor loop with 22 submaps closed into a consistent map (Sec. 5.5; Fig. 2)",[28,29,30,31,32,33,34],"Homography estimation degenerate for planar points; unstable on TUM planar floor scene (Sec. 6)","Vulnerable to outliers from VGGT points (Sec. 6)","Additional drift modes including scene perspective (Sec. 6)","Not metric scale (Sec. 1)","Images must be undistorted because lens distortion is not rectified by the homography (Sec. 6, NeurIPS version)","In the appendix the Sim(3) variant with w = 8 attains a lower TUM average ATE (0.040 m) than the SL(4) w = 32 configuration highlighted in the main text (0.053 m); SL(4) with w = 1 is numerically unstable on TUM floor and 360 (Appendix B.1; Table 6)","Calibrated baseline numbers are copied from MASt3R-SLAM and the evo trajectory alignment mode is not stated (Sec. 5.1)",[36],"monocular camera (uncalibrated)",[],"nonlinear factor-graph optimization on the SL(4) manifold estimating 15-DoF homographies between VGGT submaps","shared frames between submaps; homography estimation with 5-point RANSAC on VGGT points","discrete poses","not_applicable","SALAD image-descriptor retrieval + relative homography loop constraints","SL(4) factor graph over odometry and loop-closure constraints","VGGT dense point-cloud submaps","VGGT learned feed-forward reconstruction prior","dense point cloud and trajectory; reconstruction not in metric scale (Sec. 1)","NVIDIA GeForce RTX 4090 (24 GB) with AMD Ryzen Threadripper 7960X; per submap on office_loop with w = 16: keyframe detection 176 ms, VGGT inference 662 ms, loop-closure detection 105 ms, relative transformation 28 ms for SL(4) versus 11 ms for Sim(3), back end 0.5 ms (Table 4, NeurIPS version); VGGT alone limited to about 60 images on 24 GB (Sec. 1)","https:\u002F\u002Fgithub.com\u002FMIT-SPARK\u002FVGGT-SLAM","BSD-2-Clause",[51,55],{"relation":52,"title":53,"doi_or_url":54},"preprint","arXiv:2505.12549","https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.12549",{"relation":56,"title":57,"doi_or_url":58},"successor_preprint","VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstruction (arXiv:2601.19887); the code_url repository HEAD now documents this version","https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.19887",{"id":5,"kind":60,"shortName":7,"title":8,"authors":61,"year":9,"venue":65,"venueType":66,"publisher":67,"volumeIssuePages":68,"doi":69,"arxivId":70,"url":71,"firstPublicDate":72,"publicationStatus":16,"metadataStatus":73,"fulltextStatus":15,"era":10,"classicReason":41,"codeUrl":48,"cluster":11,"topics":74,"mdpi":75,"verification":76,"label":6,"fulltextRoute":77,"versionRead":78,"addedByCensus":75},"method",[62,63,64],"Dominic Maggio","Hyungtae Lim","Luca Carlone","Advances in Neural Information Processing Systems 38 (NeurIPS 2025)","conference","Neural Information Processing Systems Foundation","pp. 143976-144004","10.52202\u002F085713-4324","2505.12549","https:\u002F\u002Fapi.crossref.org\u002Fworks\u002F10.52202\u002F085713-4324","2025-05-18","metadata_verified",[11],false,"corrected","publisher OA","NeurIPS 2025 proceedings version of record (29-page PDF incl. appendix and checklist) read in full; arXiv v2 (23 May 2025, marked under review) also read and compared",[80,87],{"category":81,"model":82,"canonical":82,"role":83,"dataset":84,"specs":85,"locator":86},"compute","NVIDIA GeForce RTX 4090 (24 GB)","compute for runtime",null,"With AMD Ryzen Threadripper 7960X CPU; VGGT limited to about 60 images at once on this GPU","Sec. 1; Sec. 5.1; Table 4",{"category":88,"model":89,"canonical":89,"role":90,"dataset":84,"specs":91,"locator":92},"camera","not_reported (monocular cameras for custom office-loop, tabletop and bollards scenes)","method input","A single camera per scene, different scenes may use different cameras; intrinsics unknown to the method","Sec. 5.5; Appendix B.3; Appendix C.1",[94,107,115,125],{"refId":5,"refLabel":6,"fig":95,"whatZh":96,"license":97,"licenseUrl":98,"sourceUrl":99,"src":100,"width":101,"height":102,"thumb":103,"thumbWidth":104,"thumbHeight":105,"modified":106},"Fig. 1","以 Sim(3) 與 SL(4) 對齊 6 個 VGGT 子地圖的比較（Clio 公寓與隔間場景），顯示射影歧義","CC BY 4.0 (arXiv v2)","http:\u002F\u002Fcreativecommons.org\u002Flicenses\u002Fby\u002F4.0\u002F","https:\u002F\u002Farxiv.org\u002Fhtml\u002F2505.12549v2\u002Ffig\u002Fsim3_limited.png","\u002Ffigure-files\u002Fvggtslam2025\u002Ffig-1.webp",1400,764,"\u002Ffigure-files\u002Fvggtslam2025\u002Ffig-1.thumb.webp",480,262,"resized to at most 1400 px wide and converted to WebP",{"refId":5,"refLabel":6,"fig":108,"whatZh":109,"license":97,"licenseUrl":98,"sourceUrl":110,"src":111,"width":101,"height":112,"thumb":113,"thumbWidth":104,"thumbHeight":114,"modified":106},"Fig. 2","7-Scenes office 場景 8 個子地圖，以及 55 m 辦公走廊迴圈 22 個子地圖的重建與位姿","https:\u002F\u002Farxiv.org\u002Fhtml\u002F2505.12549v2\u002Ffig\u002Fsubmap.png","\u002Ffigure-files\u002Fvggtslam2025\u002Ffig-2.webp",505,"\u002Ffigure-files\u002Fvggtslam2025\u002Ffig-2.thumb.webp",173,{"refId":5,"refLabel":6,"fig":116,"whatZh":117,"license":97,"licenseUrl":98,"sourceUrl":118,"src":119,"width":120,"height":121,"thumb":122,"thumbWidth":104,"thumbHeight":123,"modified":124},"Fig. 6 (arXiv v2; Fig. 8 in NeurIPS version)","戶外儲槽周邊黃色路樁場景：Sim(3) 對齊失敗產生重影，SL(4) 可修正","https:\u002F\u002Farxiv.org\u002Fhtml\u002F2505.12549v2\u002Ffig\u002Fsim3_3.png","\u002Ffigure-files\u002Fvggtslam2025\u002Ffig-6-arxiv-v2-fig-8-in-neurips-version.webp",1289,844,"\u002Ffigure-files\u002Fvggtslam2025\u002Ffig-6-arxiv-v2-fig-8-in-neurips-version.thumb.webp",314,"converted to WebP",{"refId":5,"refLabel":6,"fig":126,"whatZh":127,"license":97,"licenseUrl":98,"sourceUrl":128,"src":129,"width":101,"height":130,"thumb":131,"thumbWidth":104,"thumbHeight":132,"modified":106},"Fig. 9 (arXiv v2; Fig. 11 in NeurIPS version)","TUM room 場景 6 個子地圖的稠密重建，相機位姿依子地圖著色","https:\u002F\u002Farxiv.org\u002Fhtml\u002F2505.12549v2\u002Ffig\u002Ftum_room.png","\u002Ffigure-files\u002Fvggtslam2025\u002Ffig-9-arxiv-v2-fig-11-in-neurips-version.webp",817,"\u002Ffigure-files\u002Fvggtslam2025\u002Ffig-9-arxiv-v2-fig-11-in-neurips-version.thumb.webp",280,{"totalRows":134,"groupCount":135,"groups":136,"others":538},27,4,[137,273,409,463],{"slug":138,"group":139,"sourceId":5,"sourceLabel":6,"table":140,"selfRows":141,"metrics":142,"seqs":148,"entrants":171,"cells":183,"outcomes":267,"locators":268,"hardware":269,"wordings":270,"notes":271},"vggtslam2025-table-2","vggtslam2025:Table 2","Table 2",10,[143],{"label":144,"unit":145,"statistic":146,"alignment":147},"ATE RMSE [m]","m","RMSE","not_reported",[149,153,155,157,159,161,163,165,167,169],{"dataset":150,"sequence":151,"environment":152},"TUM RGB-D","360","not described in the paper",{"dataset":150,"sequence":154,"environment":152},"desk",{"dataset":150,"sequence":156,"environment":152},"desk2",{"dataset":150,"sequence":158,"environment":152},"floor",{"dataset":150,"sequence":160,"environment":152},"plant",{"dataset":150,"sequence":162,"environment":152},"room",{"dataset":150,"sequence":164,"environment":152},"rpy",{"dataset":150,"sequence":166,"environment":152},"teddy",{"dataset":150,"sequence":168,"environment":152},"xyz",{"dataset":150,"sequence":170,"environment":152},"Avg",[172,176,179,181],{"name":173,"methodId":174,"linkable":175,"proposed":75,"self":75},"DROID-SLAM*","droidslam2021",true,{"name":177,"methodId":178,"linkable":175,"proposed":75,"self":75},"MASt3R-SLAM*","mast3rslam2025",{"name":180,"methodId":84,"linkable":75,"proposed":75,"self":75},"Ours (Sim(3), w = 32)",{"name":182,"methodId":5,"linkable":175,"proposed":175,"self":175},"Ours (SL(4), w = 32)",[184,188,191,194,197,199,202,205,207,210,213,215,217,219,220,221,223,225,227,229,231,233,235,236,238,240,242,243,244,246,248,250,252,253,255,257,259,261,263,265],[185,185,185,186,187,185,187,187,185],0,0.202,-1,[185,185,189,190,187,185,187,187,185],1,0.032,[185,185,192,193,187,185,187,187,185],2,0.091,[185,185,195,196,187,185,187,187,185],3,0.064,[185,185,135,198,187,185,187,187,185],0.045,[185,185,200,201,187,185,187,187,185],5,0.918,[185,185,203,204,187,185,187,187,185],6,0.056,[185,185,206,198,187,185,187,187,185],7,[185,185,208,209,187,185,187,187,185],8,0.012,[185,185,211,212,187,185,187,187,185],9,0.158,[189,185,185,214,187,185,187,187,185],0.07,[189,185,189,216,187,185,187,187,185],0.035,[189,185,192,218,187,185,187,187,185],0.055,[189,185,195,204,187,185,187,187,185],[189,185,135,216,187,185,187,187,185],[189,185,200,222,187,185,187,187,185],0.118,[189,185,203,224,187,185,187,187,185],0.041,[189,185,206,226,187,185,187,187,185],0.114,[189,185,208,228,187,185,187,187,185],0.02,[189,185,211,230,187,185,187,187,185],0.06,[192,185,185,232,187,185,187,187,185],0.123,[192,185,189,234,187,185,187,187,185],0.04,[192,185,192,218,187,185,187,187,185],[192,185,195,237,187,185,187,187,185],0.254,[192,185,135,239,187,185,187,187,185],0.022,[192,185,200,241,187,185,187,187,185],0.088,[192,185,203,224,187,185,187,187,185],[192,185,206,190,187,185,187,187,185],[192,185,208,245,187,185,187,187,185],0.016,[192,185,211,247,187,185,187,187,185],0.074,[195,185,185,249,187,185,187,187,185],0.071,[195,185,189,251,187,185,187,187,185],0.025,[195,185,192,234,187,185,187,187,185],[195,185,195,254,187,185,187,187,185],0.141,[195,185,135,256,187,185,187,187,185],0.023,[195,185,200,258,187,185,187,187,185],0.102,[195,185,203,260,187,185,187,187,185],0.03,[195,185,206,262,187,185,187,187,185],0.034,[195,185,208,264,187,185,187,187,185],0.014,[195,185,211,266,187,185,187,187,185],0.053,[],[140],[],[],[272],"ATE RMSE on TUM RGB-D (RGB only) computed with evo (alignment not stated); uncalibrated rows; floor sequence degenerate for SL(4) homography",{"slug":274,"group":275,"sourceId":5,"sourceLabel":6,"table":276,"selfRows":208,"metrics":277,"seqs":279,"entrants":296,"cells":307,"outcomes":400,"locators":401,"hardware":402,"wordings":403,"notes":404},"vggtslam2025-table-1","vggtslam2025:Table 1","Table 1",[278],{"label":144,"unit":145,"statistic":146,"alignment":147},[280,283,285,287,289,291,293,295],{"dataset":281,"sequence":282,"environment":152},"7-Scenes","chess",{"dataset":281,"sequence":284,"environment":152},"fire",{"dataset":281,"sequence":286,"environment":152},"heads",{"dataset":281,"sequence":288,"environment":152},"office",{"dataset":281,"sequence":290,"environment":152},"pumpkin",{"dataset":281,"sequence":292,"environment":152},"kitchen",{"dataset":281,"sequence":294,"environment":152},"stairs",{"dataset":281,"sequence":170,"environment":152},[297,299,301,303,304,305,306],{"name":298,"methodId":84,"linkable":75,"proposed":75,"self":75},"NICER-SLAM",{"name":300,"methodId":174,"linkable":175,"proposed":75,"self":75},"DROID-SLAM",{"name":302,"methodId":178,"linkable":175,"proposed":75,"self":75},"MASt3R-SLAM",{"name":173,"methodId":174,"linkable":175,"proposed":75,"self":75},{"name":177,"methodId":178,"linkable":175,"proposed":75,"self":75},{"name":180,"methodId":84,"linkable":75,"proposed":75,"self":75},{"name":182,"methodId":5,"linkable":175,"proposed":175,"self":175},[308,310,312,314,316,318,320,321,323,325,327,328,330,332,333,335,337,338,339,341,343,344,345,347,349,350,352,353,355,357,359,361,363,365,367,369,371,372,373,374,375,377,378,380,382,384,386,388,390,391,393,394,395,396,398,399],[185,185,185,309,187,185,187,187,185],0.033,[185,185,189,311,187,185,187,187,185],0.069,[185,185,192,313,187,185,187,187,185],0.042,[185,185,195,315,187,185,187,187,185],0.108,[185,185,135,317,187,185,187,187,185],0.2,[185,185,200,319,187,185,187,187,185],0.039,[185,185,203,315,187,185,187,187,185],[185,185,206,322,187,185,187,187,185],0.086,[189,185,185,324,187,185,187,187,185],0.036,[189,185,189,326,187,185,187,187,185],0.027,[189,185,192,251,187,185,187,187,185],[189,185,195,329,187,185,187,187,185],0.066,[189,185,135,331,187,185,187,187,185],0.127,[189,185,200,234,187,185,187,187,185],[189,185,203,334,187,185,187,187,185],0.026,[189,185,206,336,187,185,187,187,185],0.049,[192,185,185,266,187,185,187,187,185],[192,185,189,251,187,185,187,187,185],[192,185,192,340,187,185,187,187,185],0.015,[192,185,195,342,187,185,187,187,185],0.097,[192,185,135,241,187,185,187,187,185],[192,185,200,224,187,185,187,187,185],[192,185,203,346,187,185,187,187,185],0.011,[192,185,206,348,187,185,187,187,185],0.047,[195,185,185,348,187,185,187,187,189],[195,185,189,351,187,185,187,187,189],0.038,[195,185,192,262,187,185,187,187,189],[195,185,195,354,187,185,187,187,189],0.136,[195,185,135,356,187,185,187,187,189],0.166,[195,185,200,358,187,185,187,187,189],0.08,[195,185,203,360,187,185,187,187,189],0.044,[195,185,206,362,187,185,187,187,189],0.078,[135,185,185,364,187,185,187,187,192],0.063,[135,185,189,366,187,185,187,187,192],0.046,[135,185,192,368,187,185,187,187,192],0.029,[135,185,195,370,187,185,187,187,192],0.103,[135,185,135,226,187,185,187,187,192],[135,185,200,247,187,185,187,187,192],[135,185,203,190,187,185,187,187,192],[135,185,206,329,187,185,187,187,192],[200,185,185,376,187,185,187,187,195],0.037,[200,185,189,334,187,185,187,187,195],[200,185,192,379,187,185,187,187,195],0.018,[200,185,195,381,187,185,187,187,195],0.104,[200,185,135,383,187,185,187,187,195],0.133,[200,185,200,385,187,185,187,187,195],0.061,[200,185,203,387,187,185,187,187,195],0.093,[200,185,206,389,187,185,187,187,195],0.067,[203,185,185,324,187,185,187,187,195],[203,185,189,392,187,185,187,187,195],0.028,[203,185,192,379,187,185,187,187,195],[203,185,195,370,187,185,187,187,195],[203,185,135,383,187,185,187,187,195],[203,185,200,397,187,185,187,187,195],0.058,[203,185,203,387,187,185,187,187,195],[203,185,206,389,187,185,187,187,195],[],[276],[],[],[405,406,407,408],"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":410,"group":411,"sourceId":5,"sourceLabel":6,"table":412,"selfRows":200,"metrics":413,"seqs":427,"entrants":432,"cells":437,"outcomes":455,"locators":456,"hardware":458,"wordings":460,"notes":461},"vggtslam2025-table-4","vggtslam2025:Table 4","Table 4",[414,419,421,423,425],{"label":415,"unit":416,"statistic":417,"alignment":418},"Keyframe detection time [ms]","ms","mean","none",{"label":420,"unit":416,"statistic":417,"alignment":418},"VGGT inference time [ms]",{"label":422,"unit":416,"statistic":417,"alignment":418},"Loop closure detection time [ms]",{"label":424,"unit":416,"statistic":417,"alignment":418},"Relative transformation estimation time [ms]",{"label":426,"unit":416,"statistic":417,"alignment":418},"Backend optimization time [ms]",[428],{"dataset":429,"sequence":430,"environment":431},"office_loop (authors' custom sequence)","office_loop","office corridor",[433,435],{"name":434,"methodId":84,"linkable":75,"proposed":75,"self":75},"VGGT-SLAM w\u002F Sim(3)",{"name":436,"methodId":5,"linkable":175,"proposed":175,"self":175},"VGGT-SLAM w\u002F SL(4)",[438,440,441,443,444,446,447,449,451,453],[185,185,185,439,187,185,185,187,185],176,[189,185,185,439,187,185,185,187,185],[185,189,185,442,187,185,185,187,185],662,[189,189,185,442,187,185,185,187,185],[185,192,185,445,187,185,185,187,185],105,[189,192,185,445,187,185,185,187,185],[185,195,185,448,187,185,185,187,185],11,[189,195,185,450,187,185,185,187,185],28,[185,135,185,452,187,185,185,187,185],0.4,[189,135,185,454,187,185,185,187,185],0.5,[],[457],"Table 4 (NeurIPS version, Sec. 5.4)",[459],"NVIDIA GeForce RTX 4090 (24 GB) with AMD Ryzen Threadripper 7960X",[],[462],"Runtime per stage on the custom office_loop sequence with window size w = 16, averaged over five runs; stage times cover all frames of a submap (NeurIPS version only)",{"slug":464,"group":465,"sourceId":5,"sourceLabel":6,"table":466,"selfRows":135,"metrics":467,"seqs":476,"entrants":479,"cells":489,"outcomes":530,"locators":532,"hardware":533,"wordings":534,"notes":535},"vggtslam2025-table-3","vggtslam2025:Table 3","Table 3",[468,470,472,474],{"label":469,"unit":145,"statistic":146,"alignment":147},"ATE [m]",{"label":471,"unit":145,"statistic":146,"alignment":147},"Acc. [m]",{"label":473,"unit":145,"statistic":146,"alignment":147},"Complet. [m]",{"label":475,"unit":145,"statistic":146,"alignment":147},"Chamfer [m]",[477],{"dataset":281,"sequence":478,"environment":152},"7-Scenes (single aggregate column; aggregation over sequences not stated)",[480,481,482,484,486,487,488],{"name":300,"methodId":174,"linkable":175,"proposed":75,"self":75},{"name":302,"methodId":178,"linkable":175,"proposed":75,"self":75},{"name":483,"methodId":84,"linkable":75,"proposed":75,"self":75},"Spann3R @20",{"name":485,"methodId":84,"linkable":75,"proposed":75,"self":75},"Spann3R @2",{"name":177,"methodId":178,"linkable":175,"proposed":75,"self":75},{"name":180,"methodId":84,"linkable":75,"proposed":75,"self":75},{"name":182,"methodId":5,"linkable":175,"proposed":175,"self":175},[490,491,492,494,496,497,499,501,503,504,505,506,507,508,510,512,514,515,517,518,519,520,522,524,526,527,528,529],[185,185,185,336,187,185,187,187,185],[185,189,185,254,187,185,187,187,185],[185,192,185,493,187,185,187,187,185],0.048,[185,195,185,495,187,185,187,187,185],0.094,[189,185,185,348,187,185,187,187,185],[189,189,185,498,187,185,187,187,185],0.089,[189,192,185,500,187,185,187,187,185],0.085,[189,195,185,502,187,185,187,187,185],0.087,[192,185,185,84,185,185,187,187,185],[192,189,185,311,187,185,187,187,185],[192,192,185,348,187,185,187,187,185],[192,195,185,397,187,185,187,187,185],[195,185,185,84,185,185,187,187,185],[195,189,185,509,187,185,187,187,185],0.124,[195,192,185,511,187,185,187,187,185],0.043,[195,195,185,513,187,185,187,187,185],0.084,[135,185,185,329,187,185,187,187,189],[135,189,185,516,187,185,187,187,189],0.068,[135,192,185,198,187,185,187,187,189],[135,195,185,204,187,185,187,187,189],[200,185,185,389,187,185,187,187,189],[200,189,185,521,187,185,187,187,189],0.052,[200,192,185,523,187,185,187,187,189],0.062,[200,195,185,525,187,185,187,187,189],0.057,[203,185,185,389,187,185,187,187,189],[203,189,185,521,187,185,187,187,189],[203,192,185,397,187,185,187,187,189],[203,195,185,218,187,185,187,187,189],[531],"not_applicable (N\u002FA)",[466],[],[],[536,537],"Dense reconstruction on 7-Scenes following the MASt3R-SLAM protocol, RMSE in metres; calibrated; @n means a keyframe every n images","Dense reconstruction on 7-Scenes following the MASt3R-SLAM protocol, RMSE in metres; uncalibrated; @n means a keyframe every n images",[],1790510666075]