[{"data":1,"prerenderedAt":1051},["ShallowReactive",2],{"method-monogs2024":3},{"method":4,"reference":59,"equipment":80,"figures":104,"results":105},{"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":37,"platform":41,"estimator":42,"association":43,"timeModel":44,"deskew":45,"loopClosure":46,"globalOptimization":47,"mapRepresentation":48,"prior":49,"outputGeometry":50,"compute":51,"codeUrl":52,"codeLicense":53,"relatedVersions":54},"monogs2024","Matsuki et al., 2024","MonoGS (Gaussian Splatting SLAM)","Gaussian Splatting SLAM",2024,"recent","C09","odometry_with_local_mapping","MonoGS 是首個以三維高斯為唯一表示的單目 SLAM，以解析的李群雅可比直接最佳化相機位姿，並提出等向性正則化避免高斯沿視線拉長。有深度時加入幾何殘差。單目結果沒有公制尺度，評估時需做尺度對齊；地圖品質只以渲染指標評估，作者並指出高斯不顯式表示表面。","First monocular SLAM using 3D Gaussians as the sole representation, with analytic pose Jacobians and isotropic regularization; evaluated by ATE and rendering.","full_text_reviewed","peer_reviewed_published","main_body","論文未涉及營建場域；資料為 TUM RGB-D、Replica 及自錄 RealSense 序列。其基準後被營建領域研究 [yuan2026_adaptive3dgsslam] 作為基線（依該文摘要）。補充材料另以立體相機估計的深度在大尺度的 EuRoC Machine Hall 序列測試，較長且較難的序列（MH03 至 MH05）ATE 達 2.2 至 4.5 m，作者表示未來預期以迴圈閉合改善。",[20,21,22],"simulation","public_benchmark","controlled_experiment",[24,25,26,27,28],"TUM monocular average ATE 3.96 cm vs 7.73 cm for DROID-VO and 11.0 cm for DSO without loop closure (Table 1)","TUM RGB-D average ATE 1.47 cm, lowest among the rendering-based methods without loop closure (Table 1)","Replica single-process average ATE 0.32 cm (Table 2)","Forward rendering at 769 FPS vs at most 2.17 FPS for the compared implicit methods (Table 5, Supp. Table 8)","Larger camera convergence basin than hash-grid and MLP SDF maps (success ratio 0.79 to 0.82 vs 0.14 to 0.33) (Table 6)",[30,31,32,33,34,35,36],"Tested only on room-scale scenes; drift expected in larger scenes without loop closure (Supp. 12)","Not hard real-time (Supp. 12)","Surfaces not explicitly represented (Sec. 5)","With stereo depth on EuRoC Machine Hall, ATE grows to 2.2 to 4.5 m on MH03 to MH05 vs 0.02 to 0.09 m for ORB-SLAM3 (Supp. 9.5, Table 14)","Monocular TUM ATE (3.96 cm) remains worse than loop-closing DROID-SLAM (1.70 cm) and ORB-SLAM2 (1.60 cm) (Table 1)","Replica used only for RGB-D because of purely rotational camera motion; the multi-process run has 2.25 cm ATE on office4 (Sec. 4.1, Table 2)","Map quality evaluated only with rendering metrics (PSNR, SSIM, LPIPS); no geometric accuracy against ground-truth structure (Sec. 4.1)",[38,39,40],"monocular camera","RGB-D","stereo (depth from stereo, tested only on EuRoC Machine Hall in Supp. 9.5)",[],"direct photometric (plus geometric with depth) pose optimization with analytic Lie-group Jacobians; windowed keyframe mapping","direct photometric residual; depth residual when available","discrete poses","not_applicable","none (authors compare mainly against methods without loop closure)","none","anisotropic 3D Gaussians with isotropic shape regularization","none (no deep depth priors in monocular mode)","Gaussian map and renderings; authors note Gaussians do not explicitly represent the surface (Sec. 5)","Intel Core i9-12900K 3.50 GHz + NVIDIA GeForce RTX 4090; CUDA rasterisation with PyTorch for the rest; multi-process system 3.2 FPS monocular and 2.5 FPS RGB-D on TUM fr3\u002Foffice; RGB-D 1.8 FPS (multi-process) and 1.1 FPS (single-process) on Replica; up to 100 tracking iterations per frame; forward rendering 769 FPS at 1200 x 680 (Sec. 4.1, Supp. 7.1, 8.2, Tables 8-10)","https:\u002F\u002Fgithub.com\u002Fmuskie82\u002FMonoGS","MonoGS Software Licence Agreement (non-commercial, internal or academic research use)",[55],{"relation":56,"title":57,"doi_or_url":58},"preprint","arXiv:2312.06741","https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.06741",{"id":5,"kind":60,"shortName":7,"title":8,"authors":61,"year":9,"venue":66,"venueType":67,"publisher":68,"volumeIssuePages":69,"doi":70,"arxivId":71,"url":72,"firstPublicDate":73,"publicationStatus":16,"metadataStatus":74,"fulltextStatus":15,"era":10,"classicReason":45,"codeUrl":52,"cluster":11,"topics":75,"mdpi":76,"verification":77,"label":6,"fulltextRoute":78,"versionRead":79,"addedByCensus":76},"method",[62,63,64,65],"Hidenobu Matsuki","Riku Murai","Paul H. J. Kelly","Andrew J. Davison","2024 IEEE\u002FCVF Conference on Computer Vision and Pattern Recognition (CVPR)","conference","IEEE","pp. 18039-18048","10.1109\u002Fcvpr52733.2024.01708","2312.06741","https:\u002F\u002Fapi.crossref.org\u002Fworks\u002F10.1109\u002Fcvpr52733.2024.01708","2023-12-11","metadata_verified",[11],false,"confirmed","arXiv","arXiv v2 (2024-04-14) including supplementary Sec. 7-12; main-paper key values (3.96 and 1.47 cm TUM averages, 38.94 dB, 769 FPS, 3 fps, RealSense D455) cross-checked against the CVF open-access accepted version",[81,89,94,97],{"category":82,"model":83,"canonical":84,"role":85,"dataset":86,"specs":87,"locator":88},"rgbd","Intel Realsense d455","Intel RealSense D455","method input",null,"self-captured real-world sequences for qualitative monocular results","Sec. 4.1",{"category":90,"model":91,"canonical":91,"role":92,"dataset":86,"specs":93,"locator":88},"compute","Intel Core i9 12900K 3.50GHz","compute for runtime","desktop CPU",{"category":90,"model":95,"canonical":95,"role":92,"dataset":86,"specs":96,"locator":88},"NVIDIA GeForce RTX 4090","single GPU",{"category":98,"model":99,"canonical":99,"role":100,"dataset":101,"specs":102,"locator":103},"stereo_camera","stereo camera (model not named)","dataset sensor","EuRoC","depth from stereo used as input on EuRoC Machine Hall","Supp. 9.5, Table 14",[],{"totalRows":106,"groupCount":107,"groups":108,"others":907},190,31,[109,236,557,724],{"slug":110,"group":111,"sourceId":112,"sourceLabel":113,"table":114,"selfRows":115,"metrics":116,"seqs":128,"entrants":146,"cells":157,"outcomes":226,"locators":228,"hardware":231,"wordings":233,"notes":234},"gslivo2025-table-iii","gslivo2025:Table III","gslivo2025","Hong et al., 2025","Table III",18,[117,122,125],{"label":118,"unit":119,"statistic":120,"alignment":121},"RMSE\u002Fm","m","RMSE","not_reported",{"label":123,"unit":124,"statistic":121,"alignment":45},"Dur.\u002Fms","ms",{"label":126,"unit":127,"statistic":121,"alignment":45},"Mem.\u002FGB","GB",[129,133,135,139,142],{"dataset":130,"sequence":131,"environment":132},"proprietary (MoCap)","Playground01","small indoor UAV playground",{"dataset":130,"sequence":134,"environment":132},"Playground02",{"dataset":136,"sequence":137,"environment":138},"MARS-LVIG","HKisland03","aerial, island and sea",{"dataset":136,"sequence":140,"environment":141},"HKairport01","aerial, airport area",{"dataset":143,"sequence":144,"environment":145},"Oxford Spires","Radcliffe01","outdoor (Oxford Spires dataset)",[147,151,153,155],{"name":148,"methodId":149,"linkable":150,"proposed":76,"self":76},"SplaTAM","splatam2024",true,{"name":152,"methodId":5,"linkable":150,"proposed":76,"self":150},"MonoGS*",{"name":154,"methodId":5,"linkable":150,"proposed":76,"self":150},"MonoGS",{"name":156,"methodId":112,"linkable":150,"proposed":150,"self":76},"GS-LIVO (Ours)",[158,162,165,168,170,172,174,176,178,180,182,184,186,188,190,191,193,195,197,200,202,204,206,208,210,211,212,213,215,216,217,218,220,222,223,224],[159,159,159,160,161,159,161,161,159],0,0.28,-1,[159,163,159,164,161,159,159,161,159],1,612.8,[159,166,159,167,161,159,159,161,159],2,12.5,[159,159,163,169,161,159,161,161,159],0.23,[159,163,163,171,161,159,159,161,159],831.6,[159,166,163,173,161,159,159,161,159],21,[163,159,159,175,161,159,161,161,159],0.09,[163,163,159,177,161,159,159,161,159],841.5,[163,166,159,179,161,159,159,161,159],19.6,[163,159,163,181,161,159,161,161,159],0.11,[163,163,163,183,161,159,159,161,159],851.2,[163,166,163,185,161,159,159,161,159],17.2,[166,159,159,187,161,159,161,161,159],0.18,[166,163,159,189,161,159,159,161,159],541.5,[166,166,159,173,161,159,159,161,159],[166,159,163,192,161,159,161,161,159],0.17,[166,163,163,194,161,159,159,161,159],451.2,[166,166,163,196,161,159,159,161,159],18.7,[198,159,159,199,161,159,161,161,159],3,0.006,[198,163,159,201,161,159,159,161,159],48.5,[198,166,159,203,161,159,159,161,159],1.2,[198,159,163,205,161,159,161,161,159],0.005,[198,163,163,207,161,159,159,161,159],63.4,[198,166,163,209,161,159,159,161,159],1.5,[159,159,166,86,159,163,161,161,159],[163,159,166,86,159,163,161,161,159],[166,159,166,86,159,163,161,161,159],[198,159,166,214,161,163,161,161,159],0.58,[159,159,198,86,159,163,161,161,159],[163,159,198,86,159,163,161,161,159],[166,159,198,86,159,163,161,161,159],[198,159,198,219,161,163,161,161,159],0.63,[159,159,221,86,159,163,161,161,159],4,[163,159,221,86,159,163,161,161,159],[166,159,221,86,159,163,161,161,159],[198,159,221,225,161,163,161,161,159],0.75,[227],"failed (x for RMSE, duration and memory)",[229,230],"T-RO Table III; arXiv v1 Table IV","T-RO Table III",[232],"desktop, Intel i9-13900KF CPU, 128 GB RAM, NVIDIA RTX-4090 GPU",[],[235],"Gaussian-based SLAM comparison (T-RO Table III; arXiv v1 Table IV without Radcliffe01); MonoGS* uses LiDAR-projected depth, MonoGS is monocular; x = failed on all outdoor sequences (one row per failed method and sequence); Dur.\u002Fms column header carries an upward arrow in the table",{"slug":237,"group":238,"sourceId":239,"sourceLabel":240,"table":241,"selfRows":115,"metrics":242,"seqs":251,"entrants":267,"cells":285,"outcomes":550,"locators":552,"hardware":553,"wordings":554,"notes":555},"livgs2025-table-ii","livgs2025:Table II","livgs2025","Xiao et al., 2025","Table II",[243,246,249],{"label":244,"unit":245,"statistic":120,"alignment":121},"t_rel (average translational RMSE drift)","%",{"label":247,"unit":248,"statistic":120,"alignment":121},"r_rel (average rotational RMSE drift)","deg\u002F100 m",{"label":250,"unit":119,"statistic":120,"alignment":121},"t_abs (ATE RMSE)",[252,256,258,260,262,264],{"dataset":253,"sequence":254,"environment":255},"NTU4DRadLM","cp","outdoor, low-speed segment (cp about 230 m; garden and nyl segments at least 220 m each), Livox Horizon",{"dataset":253,"sequence":257,"environment":255},"garden1",{"dataset":253,"sequence":259,"environment":255},"garden2",{"dataset":253,"sequence":261,"environment":255},"nyl1",{"dataset":253,"sequence":263,"environment":255},"nyl2",{"dataset":253,"sequence":265,"environment":266},"loop2","outdoor, human-driven vehicle, high speed, 300 frames over about 250 m, Livox Horizon",[268,271,274,277,278,279,281,283],{"name":269,"methodId":270,"linkable":150,"proposed":76,"self":76},"NeRF-LOAM","nerfloam2023",{"name":272,"methodId":273,"linkable":76,"proposed":76,"self":76},"HDL-graph-SLAM","koide2019_hdlgraphslam",{"name":275,"methodId":276,"linkable":150,"proposed":76,"self":76},"ORB-SLAM3","orbslam3_2021",{"name":148,"methodId":149,"linkable":150,"proposed":76,"self":76},{"name":154,"methodId":5,"linkable":150,"proposed":76,"self":150},{"name":280,"methodId":86,"linkable":76,"proposed":76,"self":76},"Gaussian-SLAM",{"name":282,"methodId":86,"linkable":76,"proposed":76,"self":76},"GS-ICP-SLAM",{"name":284,"methodId":239,"linkable":150,"proposed":150,"self":76},"Ours",[286,288,290,292,294,296,298,300,302,304,306,308,310,312,314,316,319,321,323,325,327,329,331,333,335,337,339,341,343,345,347,349,351,353,355,357,359,361,363,365,367,369,371,373,375,377,379,381,383,385,387,389,391,393,395,396,397,399,400,401,403,404,405,407,408,409,411,412,413,415,416,417,419,421,423,425,427,429,431,433,435,437,439,441,443,444,446,448,450,452,454,456,458,460,461,462,463,464,465,466,467,468,469,470,471,472,474,476,478,481,483,485,486,488,490,492,494,496,498,500,502,504,506,508,510,512,514,517,519,521,523,525,527,529,531,533,535,537,538,540,542,544,546,548],[159,159,159,287,161,159,161,161,159],2.943,[159,163,159,289,161,159,161,161,159],9.644,[159,166,159,291,161,159,161,161,159],5.39,[159,159,163,293,161,159,161,161,159],1.182,[159,163,163,295,161,159,161,161,159],0.559,[159,166,163,297,161,159,161,161,159],0.54,[159,159,166,299,161,159,161,161,159],1.213,[159,163,166,301,161,159,161,161,159],0.707,[159,166,166,303,161,159,161,161,159],1.076,[159,159,198,305,161,159,161,161,159],1.371,[159,163,198,307,161,159,161,161,159],1.14,[159,166,198,309,161,159,161,161,159],3.504,[159,159,221,311,161,159,161,161,159],1.343,[159,163,221,313,161,159,161,161,159],1.73,[159,166,221,315,161,159,161,161,159],17.46,[159,159,317,318,161,159,161,161,159],5,1.442,[159,163,317,320,161,159,161,161,159],2.205,[159,166,317,322,161,159,161,161,159],1.785,[163,159,159,324,161,159,161,161,159],1.264,[163,163,159,326,161,159,161,161,159],1.553,[163,166,159,328,161,159,161,161,159],1.079,[163,159,163,330,161,159,161,161,159],1.874,[163,163,163,332,161,159,161,161,159],1.603,[163,166,163,334,161,159,161,161,159],1.478,[163,159,166,336,161,159,161,161,159],1.186,[163,163,166,338,161,159,161,161,159],0.88,[163,166,166,340,161,159,161,161,159],3.154,[163,159,198,342,161,159,161,161,159],1.737,[163,163,198,344,161,159,161,161,159],1.271,[163,166,198,346,161,159,161,161,159],2.266,[163,159,221,348,161,159,161,161,159],1.514,[163,163,221,350,161,159,161,161,159],1.835,[163,166,221,352,161,159,161,161,159],17.638,[163,159,317,354,161,159,161,161,159],1.436,[163,163,317,356,161,159,161,161,159],2.802,[163,166,317,358,161,159,161,161,159],0.593,[166,159,159,360,161,159,161,161,159],1.356,[166,163,159,362,161,159,161,161,159],1.992,[166,166,159,364,161,159,161,161,159],2.865,[166,159,163,366,161,159,161,161,159],1.173,[166,163,163,368,161,159,161,161,159],0.626,[166,166,163,370,161,159,161,161,159],0.529,[166,159,166,372,161,159,161,161,159],1.212,[166,163,166,374,161,159,161,161,159],0.772,[166,166,166,376,161,159,161,161,159],1.001,[166,159,198,378,161,159,161,161,159],1.342,[166,163,198,380,161,159,161,161,159],1.172,[166,166,198,382,161,159,161,161,159],19.528,[166,159,221,384,161,159,161,161,159],1.333,[166,163,221,386,161,159,161,161,159],1.736,[166,166,221,388,161,159,161,161,159],23.283,[166,159,317,390,161,159,161,161,159],1.403,[166,163,317,392,161,159,161,161,159],2.256,[166,166,317,394,161,159,161,161,159],0.952,[198,159,159,86,159,159,161,161,159],[198,163,159,86,159,159,161,161,159],[198,166,159,398,161,159,161,161,159],2.336,[198,159,163,86,159,159,161,161,159],[198,163,163,86,159,159,161,161,159],[198,166,163,402,161,159,161,161,159],0.979,[198,159,166,86,159,159,161,161,159],[198,163,166,86,159,159,161,161,159],[198,166,166,406,161,159,161,161,159],1.221,[198,159,198,86,159,159,161,161,159],[198,163,198,86,159,159,161,161,159],[198,166,198,410,161,159,161,161,159],12.332,[198,159,221,86,159,159,161,161,159],[198,163,221,86,159,159,161,161,159],[198,166,221,414,161,159,161,161,159],17.442,[198,159,317,86,159,159,161,161,159],[198,163,317,86,159,159,161,161,159],[198,166,317,418,161,159,161,161,159],2.692,[221,159,159,420,161,159,161,161,159],4.171,[221,163,159,422,161,159,161,161,159],3.472,[221,166,159,424,161,159,161,161,159],3.44,[221,159,163,426,161,159,161,161,159],1.179,[221,163,163,428,161,159,161,161,159],0.754,[221,166,163,430,161,159,161,161,159],0.664,[221,159,166,432,161,159,161,161,159],1.163,[221,163,166,434,161,159,161,161,159],0.765,[221,166,166,436,161,159,161,161,159],0.708,[221,159,198,438,161,159,161,161,159],1.382,[221,163,198,440,161,159,161,161,159],1.175,[221,166,198,442,161,159,161,161,159],9.595,[221,159,221,305,161,159,161,161,159],[221,163,221,445,161,159,161,161,159],1.701,[221,166,221,447,161,159,161,161,159],28.553,[221,159,317,449,161,159,161,161,159],7.375,[221,163,317,451,161,159,161,161,159],5.708,[221,166,317,453,161,159,161,161,159],15.357,[317,159,159,455,161,159,161,161,159],1.249,[317,163,159,457,161,159,161,161,159],3.047,[317,166,159,459,161,159,161,161,159],1.04,[317,159,163,86,159,159,161,161,159],[317,163,163,86,159,159,161,161,159],[317,166,163,86,159,159,161,161,159],[317,159,166,86,159,159,161,161,159],[317,163,166,86,159,159,161,161,159],[317,166,166,86,159,159,161,161,159],[317,159,198,86,159,159,161,161,159],[317,163,198,86,159,159,161,161,159],[317,166,198,86,159,159,161,161,159],[317,159,221,86,159,159,161,161,159],[317,163,221,86,159,159,161,161,159],[317,166,221,86,159,159,161,161,159],[317,159,317,473,161,159,161,161,159],1.399,[317,163,317,475,161,159,161,161,159],2.384,[317,166,317,477,161,159,161,161,159],1.136,[479,159,159,480,161,159,161,161,159],6,5.471,[479,163,159,482,161,159,161,161,159],4.041,[479,166,159,484,161,159,161,161,159],6.33,[479,159,163,455,161,159,161,161,159],[479,163,163,487,161,159,161,161,159],0.764,[479,166,163,489,161,159,161,161,159],2.082,[479,159,166,491,161,159,161,161,159],1.824,[479,163,166,493,161,159,161,161,159],1.316,[479,166,166,495,161,159,161,161,159],5.507,[479,159,198,497,161,159,161,161,159],1.662,[479,163,198,499,161,159,161,161,159],1.771,[479,166,198,501,161,159,161,161,159],23.331,[479,159,221,503,161,159,161,161,159],2.101,[479,163,221,505,161,159,161,161,159],1.07,[479,166,221,507,161,159,161,161,159],23.915,[479,159,317,509,161,159,161,161,159],3.236,[479,163,317,511,161,159,161,161,159],2.644,[479,166,317,513,161,159,161,161,159],13.819,[515,159,159,516,161,159,161,161,159],7,0.234,[515,163,159,518,161,159,161,161,159],1.216,[515,166,159,520,161,159,161,161,159],0.464,[515,159,163,522,161,159,161,161,159],1.183,[515,163,163,524,161,159,161,161,159],0.716,[515,166,163,526,161,159,161,161,159],0.366,[515,159,166,528,161,159,161,161,159],1.236,[515,163,166,530,161,159,161,161,159],0.962,[515,166,166,532,161,159,161,161,159],0.679,[515,159,198,534,161,159,161,161,159],1.24,[515,163,198,536,161,159,161,161,159],1.307,[515,166,198,214,161,159,161,161,159],[515,159,221,539,161,159,161,161,159],1.106,[515,163,221,541,161,159,161,161,159],1.369,[515,166,221,543,161,159,161,161,159],0.771,[515,159,317,545,161,159,161,161,159],1.393,[515,163,317,547,161,159,161,161,159],2.239,[515,166,317,549,161,159,161,161,159],0.843,[551],"not reported ('-' in table)",[241],[],[],[556],"Tracking accuracy with rpg trajectory evaluation: t_rel = average translational RMSE drift (%), r_rel = average rotational RMSE drift (deg\u002F100 m), t_abs = ATE RMSE (m); reference trajectories from R3LIVE (not an independent measurement); alignment not stated; IMU not used by LiV-GS; '-' entries reported without explanation (text says indoor-oriented 3DGS SLAM methods degrade or fail on some outdoor sequences)",{"slug":558,"group":559,"sourceId":5,"sourceLabel":6,"table":560,"selfRows":115,"metrics":561,"seqs":566,"entrants":587,"cells":606,"outcomes":718,"locators":719,"hardware":720,"wordings":721,"notes":722},"monogs2024-table-2","monogs2024:Table 2","Table 2",[562],{"label":563,"unit":564,"statistic":120,"alignment":565},"ATE RMSE (keyframes)","cm","SE3",[567,571,573,575,577,579,581,583,585],{"dataset":568,"sequence":569,"environment":570},"Replica","room0","synthetic Replica sequences (room0 to room2, office0 to office4) with purely rotational camera motion, RGB-D input",{"dataset":568,"sequence":572,"environment":570},"room1",{"dataset":568,"sequence":574,"environment":570},"room2",{"dataset":568,"sequence":576,"environment":570},"office0",{"dataset":568,"sequence":578,"environment":570},"office1",{"dataset":568,"sequence":580,"environment":570},"office2",{"dataset":568,"sequence":582,"environment":570},"office3",{"dataset":568,"sequence":584,"environment":570},"office4",{"dataset":568,"sequence":586,"environment":570},"Avg.",[588,591,594,596,599,602,604],{"name":589,"methodId":590,"linkable":150,"proposed":76,"self":76},"iMAP [35]","imap2021",{"name":592,"methodId":593,"linkable":150,"proposed":76,"self":76},"NICE-SLAM","niceslam2022",{"name":595,"methodId":86,"linkable":76,"proposed":76,"self":76},"Vox-Fusion [45]",{"name":597,"methodId":598,"linkable":150,"proposed":76,"self":76},"ESLAM [9]","eslam2023",{"name":600,"methodId":601,"linkable":150,"proposed":76,"self":76},"Point-SLAM [29]","pointslam2023",{"name":603,"methodId":5,"linkable":150,"proposed":150,"self":150},"MonoGS (Ours, multi-process)",{"name":605,"methodId":5,"linkable":150,"proposed":150,"self":150},"MonoGS (Ours sp, single-process)",[607,609,611,613,615,617,619,621,623,626,628,630,631,632,633,635,637,639,640,642,644,646,648,650,651,653,655,657,659,661,663,665,667,668,670,671,672,674,676,678,680,682,683,685,686,688,690,692,694,695,696,697,698,700,701,703,705,707,709,711,713,715,717],[159,159,159,608,161,159,161,161,159],3.12,[159,159,163,610,161,159,161,161,159],2.54,[159,159,166,612,161,159,161,161,159],2.31,[159,159,198,614,161,159,161,161,159],1.69,[159,159,221,616,161,159,161,161,159],1.03,[159,159,317,618,161,159,161,161,159],3.99,[159,159,479,620,161,159,161,161,159],4.05,[159,159,515,622,161,159,161,161,159],1.93,[159,159,624,625,161,159,161,161,159],8,2.58,[163,159,159,627,161,159,161,161,159],0.97,[163,159,163,629,161,159,161,161,159],1.31,[163,159,166,505,161,159,161,161,159],[163,159,198,338,161,159,161,161,159],[163,159,221,163,161,159,161,161,159],[163,159,317,634,161,159,161,161,159],1.06,[163,159,479,636,161,159,161,161,159],1.1,[163,159,515,638,161,159,161,161,159],1.13,[163,159,624,505,161,159,161,161,159],[166,159,159,641,161,159,161,161,159],1.37,[166,159,163,643,161,159,161,161,159],4.7,[166,159,166,645,161,159,161,161,159],1.47,[166,159,198,647,161,159,161,161,159],8.48,[166,159,221,649,161,159,161,161,159],2.04,[166,159,317,625,161,159,161,161,159],[166,159,479,652,161,159,161,161,159],1.11,[166,159,515,654,161,159,161,161,159],2.94,[166,159,624,656,161,159,161,161,159],3.09,[198,159,159,658,161,159,161,161,159],0.71,[198,159,163,660,161,159,161,161,159],0.7,[198,159,166,662,161,159,161,161,159],0.52,[198,159,198,664,161,159,161,161,159],0.57,[198,159,221,666,161,159,161,161,159],0.55,[198,159,317,214,161,159,161,161,159],[198,159,479,669,161,159,161,161,159],0.72,[198,159,515,219,161,159,161,161,159],[198,159,624,219,161,159,161,161,159],[221,159,159,673,161,159,161,161,159],0.61,[221,159,163,675,161,159,161,161,159],0.41,[221,159,166,677,161,159,161,161,159],0.37,[221,159,198,679,161,159,161,161,159],0.38,[221,159,221,681,161,159,161,161,159],0.48,[221,159,317,297,161,159,161,161,159],[221,159,479,684,161,159,161,161,159],0.69,[221,159,515,669,161,159,161,161,159],[221,159,624,687,161,159,161,161,159],0.53,[317,159,159,689,161,159,161,161,159],0.44,[317,159,163,691,161,159,161,161,159],0.32,[317,159,166,693,161,159,161,161,159],0.31,[317,159,198,689,161,159,161,161,159],[317,159,221,662,161,159,161,161,159],[317,159,317,169,161,159,161,161,159],[317,159,479,192,161,159,161,161,159],[317,159,515,699,161,159,161,161,159],2.25,[317,159,624,214,161,159,161,161,159],[479,159,159,702,161,159,161,161,159],0.33,[479,159,163,704,161,159,161,161,159],0.22,[479,159,166,706,161,159,161,161,159],0.29,[479,159,198,708,161,159,161,161,159],0.36,[479,159,221,710,161,159,161,161,159],0.19,[479,159,317,712,161,159,161,161,159],0.25,[479,159,479,714,161,159,161,161,159],0.12,[479,159,515,716,161,159,161,161,159],0.81,[479,159,624,691,161,159,161,161,159],[],[560],[],[],[723],"Keyframe ATE RMSE (cm) on Replica, RGB-D only (Replica has purely rotational motions); baselines from Point-SLAM; Ours = multi-process real-time implementation, Ours (sp) = single-process with more mapping iterations.",{"slug":725,"group":726,"sourceId":727,"sourceLabel":728,"table":729,"selfRows":730,"metrics":731,"seqs":741,"entrants":769,"cells":780,"outcomes":901,"locators":902,"hardware":903,"wordings":904,"notes":905},"gaussianlic2025-table-i","gaussianlic2025:Table I","gaussianlic2025","Lang et al., 2025","Table I",12,[732,735,739],{"label":733,"unit":734,"statistic":121,"alignment":45},"PSNR (dB)","dB",{"label":736,"unit":737,"statistic":738,"alignment":45},"SSIM, Avg. column","unitless","mean",{"label":740,"unit":737,"statistic":738,"alignment":45},"LPIPS, Avg. column",[742,746,748,750,753,755,757,760,762,764,767],{"dataset":743,"sequence":744,"environment":745},"FAST-LIVO","f0 hku2","real-world indoor and outdoor sequences (FAST-LIVO, R3LIVE, MCD)",{"dataset":743,"sequence":747,"environment":745},"f1 LiDAR Degenerate",{"dataset":743,"sequence":749,"environment":745},"f2 Visual Challenge",{"dataset":751,"sequence":752,"environment":745},"R3LIVE","r0 hku_campus_seq_00",{"dataset":751,"sequence":754,"environment":745},"r1 degenerate_seq_00",{"dataset":751,"sequence":756,"environment":745},"r2 degenerate_seq_01",{"dataset":758,"sequence":759,"environment":745},"MCD","m0 tuhh_day_02 segment",{"dataset":758,"sequence":761,"environment":745},"m1 tuhh_day_03 segment",{"dataset":758,"sequence":763,"environment":745},"m2 tuhh_day_04 segment",{"dataset":765,"sequence":766,"environment":745},"FAST-LIVO, R3LIVE and MCD","Avg. average",{"dataset":765,"sequence":768,"environment":745},"average of 9 sequences",[770,772,774,776,778],{"name":771,"methodId":86,"linkable":76,"proposed":76,"self":76},"NeRF-SLAM (train view)",{"name":773,"methodId":5,"linkable":150,"proposed":76,"self":150},"MonoGS (train view)",{"name":775,"methodId":149,"linkable":150,"proposed":76,"self":76},"SplaTAM with LiDAR pseudo RGB-D (train view)",{"name":777,"methodId":727,"linkable":150,"proposed":150,"self":76},"Gaussian-LIC (train view)",{"name":779,"methodId":727,"linkable":150,"proposed":150,"self":76},"Gaussian-LIC (novel view)",[781,783,785,787,789,791,793,794,796,798,801,803,805,807,809,811,813,815,817,819,821,823,825,827,829,831,833,835,837,839,841,843,845,847,849,851,853,855,857,859,861,863,865,867,869,871,873,875,877,879,881,884,886,888,889,891,893,895,897,899],[159,159,159,782,161,159,161,161,159],25.56,[159,159,163,784,161,159,161,161,159],25.47,[159,159,166,786,161,159,161,161,159],17.01,[159,159,198,788,161,159,161,161,159],19.53,[159,159,221,790,161,159,161,161,159],21.2,[159,159,317,792,161,159,161,161,159],15.02,[159,159,479,196,161,159,161,161,159],[159,159,515,795,161,159,161,161,159],18.93,[159,159,624,797,161,159,161,161,159],15.4,[159,159,799,800,161,159,161,161,159],9,19.65,[163,159,159,802,161,159,161,161,159],23.58,[163,159,163,804,161,159,161,161,159],23.45,[163,159,166,806,161,159,161,161,159],17.04,[163,159,198,808,161,159,161,161,159],16.19,[163,159,221,810,161,159,161,161,159],15.03,[163,159,317,812,161,159,161,161,159],15.09,[163,159,479,814,161,159,161,161,159],16.41,[163,159,515,816,161,159,161,161,159],13.69,[163,159,624,818,161,159,161,161,159],14.91,[163,159,799,820,161,159,161,161,159],17.27,[166,159,159,822,161,159,161,161,159],25.51,[166,159,163,824,161,159,161,161,159],27.4,[166,159,166,826,161,159,161,161,159],17.84,[166,159,198,828,161,159,161,161,159],17.1,[166,159,221,830,161,159,161,161,159],19.24,[166,159,317,832,161,159,161,161,159],18.3,[166,159,479,834,161,159,161,161,159],13.68,[166,159,515,836,161,159,161,161,159],13.17,[166,159,624,838,161,159,161,161,159],10.01,[166,159,799,840,161,159,161,161,159],18.03,[198,159,159,842,161,159,161,161,159],29.89,[198,159,163,844,161,159,161,161,159],31.28,[198,159,166,846,161,159,161,161,159],23.9,[198,159,198,848,161,159,161,161,159],25.27,[198,159,221,850,161,159,161,161,159],22.47,[198,159,317,852,161,159,161,161,159],23.49,[198,159,479,854,161,159,161,161,159],21.06,[198,159,515,856,161,159,161,161,159],22.87,[198,159,624,858,161,159,161,161,159],20.73,[198,159,799,860,161,159,161,161,159],24.55,[221,159,159,862,161,159,161,161,159],29.28,[221,159,163,864,161,159,161,161,159],30.91,[221,159,166,866,161,159,161,161,159],23.28,[221,159,198,868,161,159,161,161,159],24.52,[221,159,221,870,161,159,161,161,159],22.03,[221,159,317,872,161,159,161,161,159],22.59,[221,159,479,874,161,159,161,161,159],20.19,[221,159,515,876,161,159,161,161,159],22.12,[221,159,624,878,161,159,161,161,159],19.57,[221,159,799,880,161,159,161,161,159],23.83,[159,163,882,883,161,159,161,161,159],10,0.603,[159,166,882,885,161,159,161,161,159],0.405,[163,163,882,887,161,159,161,161,159],0.548,[163,166,882,658,161,159,161,161,159],[166,163,882,890,161,159,161,161,159],0.592,[166,166,882,892,161,159,161,161,159],0.361,[198,163,882,894,161,159,161,161,159],0.77,[198,166,882,896,161,159,161,161,159],0.231,[221,163,882,898,161,159,161,161,159],0.738,[221,166,882,900,161,159,161,161,159],0.236,[],[729],[],[],[906],"Rendering quality; compared methods mapped with ground-truth poses (MCD) or Gaussian-LIC estimated poses (FAST-LIVO, R3LIVE); FAST-LIVO and R3LIVE use a solid-state LiDAR, MCD a spinning LiDAR",[908,918,923,929,934,940,945,950,957,963,969,977,982,986,990,994,999,1003,1007,1012,1017,1021,1027,1031,1036,1041,1046],{"group":909,"slug":910,"sourceLabel":911,"table":912,"selfRows":730,"datasets":913},"gslivm2025:Table 1","gslivm2025-table-1","Xie et al., 2025","Table 1",[914,915,916,917],"Botanic Garden","FAST-LIVO dataset (row-to-dataset mapping inferred from caption order)","NTU-VIRAL","R3LIVE dataset",{"group":919,"slug":920,"sourceLabel":921,"table":912,"selfRows":799,"datasets":922},"gsicpslam2024:Table 1","gsicpslam2024-table-1","Ha et al., 2024",[568],{"group":924,"slug":925,"sourceLabel":926,"table":114,"selfRows":799,"datasets":927},"yan2026_underground3dgsslam:Table III","yan2026-underground3dgsslam-table-iii","Yan et al., 2026b",[928],"Underground_RGB-D (authors' field test dataset)",{"group":930,"slug":931,"sourceLabel":6,"table":912,"selfRows":624,"datasets":932},"monogs2024:Table 1","monogs2024-table-1",[933],"TUM RGB-D",{"group":935,"slug":936,"sourceLabel":937,"table":938,"selfRows":515,"datasets":939},"deng2026_mcgs_slam:Table 3","deng2026-mcgs-slam-table-3","Deng & Gan, 2026","Table 3",[568],{"group":941,"slug":942,"sourceLabel":937,"table":943,"selfRows":515,"datasets":944},"deng2026_mcgs_slam:Table 8","deng2026-mcgs-slam-table-8","Table 8",[568],{"group":946,"slug":947,"sourceLabel":113,"table":729,"selfRows":479,"datasets":948},"gslivo2025:Table I","gslivo2025-table-i",[949,136,130],"FAST-LIVO2 dataset",{"group":951,"slug":952,"sourceLabel":953,"table":954,"selfRows":479,"datasets":955},"yuan2026_adaptive3dgsslam:Table 4","yuan2026-adaptive3dgsslam-table-4","Yuan et al., 2026","Table 4",[956],"ReplicaCAD (FRL apartment)",{"group":958,"slug":959,"sourceLabel":953,"table":960,"selfRows":479,"datasets":961},"yuan2026_adaptive3dgsslam:Table 5","yuan2026-adaptive3dgsslam-table-5","Table 5",[962],"authors' real-world RGB-D dataset",{"group":964,"slug":965,"sourceLabel":937,"table":966,"selfRows":317,"datasets":967},"deng2026_mcgs_slam:Table 11","deng2026-mcgs-slam-table-11","Table 11",[968],"EuRoC MAV",{"group":970,"slug":971,"sourceLabel":911,"table":972,"selfRows":317,"datasets":973},"gslivm2025:Supp. Table 5","gslivm2025-supp-table-5","Supp. Table 5",[914,974,975,976],"FAST-LIVO or R3LIVE dataset (not stated)","not stated","self-collected",{"group":978,"slug":979,"sourceLabel":6,"table":980,"selfRows":317,"datasets":981},"monogs2024:Table 14","monogs2024-table-14","Table 14",[101],{"group":983,"slug":984,"sourceLabel":728,"table":241,"selfRows":221,"datasets":985},"gaussianlic2025:Table II","gaussianlic2025-table-ii",[743],{"group":987,"slug":988,"sourceLabel":921,"table":560,"selfRows":221,"datasets":989},"gsicpslam2024:Table 2","gsicpslam2024-table-2",[933],{"group":991,"slug":992,"sourceLabel":921,"table":938,"selfRows":221,"datasets":993},"gsicpslam2024:Table 3","gsicpslam2024-table-3",[568],{"group":995,"slug":996,"sourceLabel":6,"table":997,"selfRows":221,"datasets":998},"monogs2024:Supp. Tables 9-10","monogs2024-supp-tables-9-10","Supp. Tables 9-10",[568,933],{"group":1000,"slug":1001,"sourceLabel":953,"table":938,"selfRows":221,"datasets":1002},"yuan2026_adaptive3dgsslam:Table 3","yuan2026-adaptive3dgsslam-table-3",[956],{"group":1004,"slug":1005,"sourceLabel":937,"table":912,"selfRows":198,"datasets":1006},"deng2026_mcgs_slam:Table 1","deng2026-mcgs-slam-table-1",[933],{"group":1008,"slug":1009,"sourceLabel":240,"table":1010,"selfRows":198,"datasets":1011},"livgs2025:Table IV","livgs2025-table-iv","Table IV",[917],{"group":1013,"slug":1014,"sourceLabel":926,"table":1015,"selfRows":198,"datasets":1016},"yan2026_underground3dgsslam:Table VI","yan2026-underground3dgsslam-table-vi","Table VI",[933],{"group":1018,"slug":1019,"sourceLabel":953,"table":912,"selfRows":198,"datasets":1020},"yuan2026_adaptive3dgsslam:Table 1","yuan2026-adaptive3dgsslam-table-1",[568],{"group":1022,"slug":1023,"sourceLabel":911,"table":1024,"selfRows":166,"datasets":1025},"gslivm2025:ICCV Supp. Table 5","gslivm2025-iccv-supp-table-5","ICCV Supp. Table 5",[1026,917],"FAST-LIVO dataset (row-to-dataset mapping inferred from Table 1 caption order)",{"group":1028,"slug":1029,"sourceLabel":937,"table":560,"selfRows":163,"datasets":1030},"deng2026_mcgs_slam:Table 2","deng2026-mcgs-slam-table-2",[933],{"group":1032,"slug":1033,"sourceLabel":937,"table":1034,"selfRows":163,"datasets":1035},"deng2026_mcgs_slam:Table 9","deng2026-mcgs-slam-table-9","Table 9",[933],{"group":1037,"slug":1038,"sourceLabel":911,"table":1039,"selfRows":163,"datasets":1040},"gslivm2025:ICCV Supp. Table 6","gslivm2025-iccv-supp-table-6","ICCV Supp. Table 6",[975],{"group":1042,"slug":1043,"sourceLabel":1044,"table":729,"selfRows":163,"datasets":1045},"hislam2_2025:Table I","hislam2-2025-table-i","Zhang et al., 2025",[568],{"group":1047,"slug":1048,"sourceLabel":1044,"table":114,"selfRows":163,"datasets":1049},"hislam2_2025:Table III","hislam2-2025-table-iii",[1050],"Waymo Open",1790510665417]