[{"data":1,"prerenderedAt":586},["ShallowReactive",2],{"method-gslivm2025":3},{"method":4,"reference":58,"equipment":79,"figures":137,"results":138},{"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":26,"sensors":34,"platform":38,"estimator":41,"association":42,"timeModel":43,"deskew":44,"loopClosure":45,"globalOptimization":46,"mapRepresentation":47,"prior":48,"outputGeometry":49,"compute":50,"codeUrl":51,"codeLicense":52,"relatedVersions":53},"gslivm2025","Xie et al., 2025","GS-LIVM","GS-LIVM: Real-Time Photo-Realistic LiDAR-Inertial-Visual Mapping with Gaussian Splatting",2025,"recent","C09","map_representation_or_reconstruction","GS-LIVM 以改良的 SR-LIVO（ESIKF 緊耦合 LiDAR、慣性與視覺里程計）提供位姿，在體素層級以高斯過程回歸（Voxel-GPR）把稀疏且分布不均的 LiDAR 點轉為均勻網格點，並以預測變異數加權計算三維高斯的初始位置與尺度（旋轉設為單位四元數），再以影像、深度差與結構相似損失持續最佳化，在 8 GB 筆電 GPU 上完成大型戶外場景的即時寫實建圖。論文只評估渲染品質與軌跡，作者指出高斯初始化完全依賴點雲，LiDAR 未覆蓋處會出現缺漏。","Uses voxel-level GPR on sparse LiDAR points to initialize covariance-aware 3D Gaussians for real-time outdoor photorealistic mapping on top of LIVO poses.","full_text_reviewed","peer_reviewed_published","supplementary","論文未在營建場域測試；資料為 R3LIVE、FAST-LIVO、NTU-VIRAL、Botanic Garden，以及作者以 Livox MID-360 與 HESAI Pandar XT-32 自錄的兩段序列。論文只評估渲染品質、資源用量與軌跡，未量測地圖幾何精度，因此無法直接支持營建量測用途。",[20],"public_benchmark",[22,23,24,25],"Real-time photorealistic mapping in large unbounded outdoor scenes (abstract)","Best LPIPS on all four Table 1 sequences and best PSNR on three of four under the 100-frame, 5-minute comparison protocol (Table 1)","Full sequences mapped on an 8 GB laptop GPU, including a 1170 s, about 900 m sequence in real time with nr = 2 (Sec. 4.3; Supp. 7.2, 7.5; Table 8)","The authors' improved SR-LIVO tracker has the lowest RPE on all seven Botanic Garden sequences and the lowest ATE on two of seven (Supp. Table 7)",[27,28,29,30,31,32,33],"Initialization relies solely on point clouds, leaving missing regions without LiDAR coverage (Supp. 8)","Real-time constraints limit reconstruction quality (Supp. 8)","No loop closure; ATE higher than LVI-SAM on five of seven Botanic Garden sequences (Supp. 7.4, Table 7)","A fully optimized offline 3DGS scores higher on training views (hku seq 00 PSNR 27.827 vs 22.430), although the authors report poorer novel-view synthesis for it (Supp. 7.1, Table 4, Fig. 8)","Rendering from sparse spinning LiDAR is worse than from Livox LiDAR; 3DGS has higher PSNR than GS-LIVM on all five additional sequences of Supp. Table 5 (Supp. 7.2)","Baselines in Table 1 were run on reduced scenes (at most 100 frames, 5 min) with COLMAP poses and depth, while GS-LIVM used its own odometry (Sec. 4.2)","Sky regions receive no LiDAR returns and are excluded; handling them is left to future work (ICCV Supp. 8; absent from arXiv v1)",[35,36,37],"3D LiDAR","IMU","monocular camera",[39,40],"handheld","wheeled robot","ESIKF LiDAR-inertial-visual odometry (tracking thread, output at IMU rate) adopted from SR-LIVO [48] with two changes: original sensor timestamps replace the time-sweep refinement (fixing crashes with spinning LiDAR) and large matrix products are CUDA-accelerated","colour point cloud from LIVO; photometric, SSIM, structure-similarity and delta-depth losses for Gaussian optimization","discrete poses","not_applicable","none; the authors state the tracking method lacks a loop closure detection module and is less accurate than LVI-SAM on some Botanic Garden sequences","none reported","voxel-hashed dense map of 3D Gaussians (position, covariance, opacity, zero-degree SH colour) initialized per voxel subgrid from Voxel-GPR predictions: position as the inverse-variance weighted mean, scale from the diagonal of the weighted covariance, rotation set to the identity quaternion","none","dense 3D Gaussian map and rendered images; no geometric accuracy metric of the map is reported (evaluation covers PSNR, SSIM, LPIPS, runtime, memory and trajectory RPE and ATE only)","CUDA\u002FC++ with LibTorch under ROS; desktop PC with a 5.50 GHz Intel Core i9-13900HX CPU, 64 GB RAM and an NVIDIA RTX 4060 Laptop 8 GB GPU; Voxel-GPR under 30 ms per batch; all sequences fully mapped on the 8 GB GPU with ns = 3; mapping time equals or nearly equals the sequence duration (e.g., 612 s for a 611 s sequence)","https:\u002F\u002Fgithub.com\u002Fxieyuser\u002FGS-LIVM","GPL-3.0",[54],{"relation":55,"title":56,"doi_or_url":57},"preprint","arXiv:2410.17084","https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.17084",{"id":5,"kind":59,"shortName":7,"title":8,"authors":60,"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":44,"codeUrl":51,"cluster":11,"topics":74,"mdpi":75,"verification":76,"label":6,"fulltextRoute":77,"versionRead":78,"addedByCensus":75},"method",[61,62,63,64],"Yusen Xie","Zhenmin Huang","Jin Wu","Jun Ma","2025 IEEE\u002FCVF International Conference on Computer Vision (ICCV)","conference","IEEE","pp. 26869-26878","10.1109\u002Ficcv51701.2025.02494","2410.17084","https:\u002F\u002Fapi.crossref.org\u002Fworks\u002F10.1109\u002Ficcv51701.2025.02494","2024-10-18","metadata_verified",[11],false,"confirmed","publisher OA","ICCV 2025 CVF Open Access version (main paper, pp. 26869-26876; identical to the accepted version except the watermark) plus the supplementary material as included in arXiv v1 (2024-10-18, pages 11-15); second checker additionally read the ICCV 2025 supplementary PDF (11855_supp.pdf, 6 pages, taken from the CVF supplemental zip by HTTP range request) besides the CVF main paper and arXiv v1 HTML",[80,87,91,95,99,104,106,109,112,118,122,128,132,135],{"category":81,"model":82,"canonical":82,"role":83,"dataset":84,"specs":85,"locator":86},"lidar","Livox Avia","dataset sensor","R3LIVE dataset; FAST-LIVO dataset","10 Hz; handheld device with built-in IMU and a 15 Hz RGB camera (640 x 512)","Sec. 4.1",{"category":88,"model":89,"canonical":89,"role":83,"dataset":84,"specs":90,"locator":86},"imu","Livox Avia built-in IMU","200 Hz",{"category":92,"model":93,"canonical":93,"role":83,"dataset":84,"specs":94,"locator":86},"camera","RGB camera (model not reported)","15 Hz, 640 x 512",{"category":81,"model":96,"canonical":96,"role":83,"dataset":97,"specs":98,"locator":86},"Ouster-16","NTU-VIRAL","multi-line spinning LiDAR, sparser than Livox; images 752 x 480",{"category":81,"model":100,"canonical":100,"role":83,"dataset":101,"specs":102,"locator":103},"Velodyne VLP-16","Botanic Garden","multi-line spinning LiDAR; images 480 x 300; used for the tracking evaluation","Sec. 4.1; Supp. 7.4",{"category":81,"model":82,"canonical":82,"role":83,"dataset":101,"specs":105,"locator":86},"second LiDAR on the Botanic Garden robot",{"category":107,"model":40,"canonical":40,"role":83,"dataset":101,"specs":108,"locator":86},"platform","traverses a botanic garden",{"category":107,"model":110,"canonical":110,"role":83,"dataset":84,"specs":111,"locator":86},"handheld device","Livox Avia, built-in IMU and RGB camera",{"category":81,"model":113,"canonical":113,"role":114,"dataset":115,"specs":116,"locator":117},"Livox MID-360","method input",null,"self-collected sequence 'private-360', images 640 x 512","Supp. 7.2",{"category":81,"model":119,"canonical":120,"role":114,"dataset":115,"specs":121,"locator":117},"HESAI Pandar XT-32","Hesai PandarXT-32","self-collected sequence 'private-pandar', images 640 x 512",{"category":123,"model":124,"canonical":124,"role":125,"dataset":115,"specs":126,"locator":127},"compute","Intel Core i9-13900HX","compute for runtime","5.50 GHz CPU, 64 GB RAM desktop PC","Sec. 4.1 Implementation Details",{"category":123,"model":129,"canonical":129,"role":125,"dataset":115,"specs":130,"locator":131},"NVIDIA RTX 4060 Laptop 8 GB GPU","8 GB","Sec. 4.1 Implementation Details; Sec. 4.3",{"category":92,"model":133,"canonical":133,"role":83,"dataset":97,"specs":134,"locator":86},"camera (model not reported)","image resolution 752 x 480",{"category":92,"model":133,"canonical":133,"role":83,"dataset":101,"specs":136,"locator":86},"image resolution 480 x 300",[],{"totalRows":139,"groupCount":140,"groups":141,"others":556},64,9,[142,310,448,510],{"slug":143,"group":144,"sourceId":5,"sourceLabel":6,"table":145,"selfRows":146,"metrics":147,"seqs":153,"entrants":169,"cells":182,"outcomes":303,"locators":304,"hardware":306,"wordings":307,"notes":308},"gslivm2025-supp-table-7","gslivm2025:Supp. Table 7","Supp. Table 7",14,[148,151],{"label":149,"unit":150,"statistic":150,"alignment":150},"RPE (full transformation)","not_reported",{"label":152,"unit":150,"statistic":150,"alignment":150},"ATE (full transformation)",[154,157,159,161,163,165,167],{"dataset":101,"sequence":155,"environment":156},"1005 00","outdoor botanic garden, wheeled robot, Velodyne VLP-16",{"dataset":101,"sequence":158,"environment":156},"1005 01",{"dataset":101,"sequence":160,"environment":156},"1005 07",{"dataset":101,"sequence":162,"environment":156},"1006 01",{"dataset":101,"sequence":164,"environment":156},"1008 03",{"dataset":101,"sequence":166,"environment":156},"1018 00",{"dataset":101,"sequence":168,"environment":156},"1018 13",[170,174,177,180],{"name":171,"methodId":172,"linkable":173,"proposed":75,"self":75},"R3LIVE [18]","r3live2022",true,{"name":175,"methodId":176,"linkable":173,"proposed":75,"self":75},"FAST-LIO2 [43]","fastlio2_2022",{"name":178,"methodId":179,"linkable":173,"proposed":75,"self":75},"LVI-SAM [33]","lvisam2021",{"name":181,"methodId":5,"linkable":173,"proposed":173,"self":173},"OURS",[183,187,190,192,194,197,199,202,204,207,209,212,214,217,219,221,223,225,227,229,231,233,235,237,239,241,243,245,247,249,251,253,255,257,259,261,263,265,267,269,271,273,275,277,279,281,283,285,287,289,291,293,295,297,299,301],[184,184,184,185,186,184,186,186,184],0,1.165,-1,[184,188,184,189,186,184,186,186,184],1,3.153,[184,184,188,191,186,184,186,186,184],1.151,[184,188,188,193,186,184,186,186,184],1.451,[184,184,195,196,186,184,186,186,184],2,2.112,[184,188,195,198,186,184,186,186,184],3.893,[184,184,200,201,186,184,186,186,184],3,0.934,[184,188,200,203,186,184,186,186,184],3.505,[184,184,205,206,186,184,186,186,184],4,2.05,[184,188,205,208,186,184,186,186,184],3.383,[184,184,210,211,186,184,186,186,184],5,0.165,[184,188,210,213,186,184,186,186,184],0.378,[184,184,215,216,186,184,186,186,184],6,0.133,[184,188,215,218,186,184,186,186,184],0.366,[188,184,184,220,186,184,186,186,184],1.048,[188,188,184,222,186,184,186,186,184],2.665,[188,184,188,224,186,184,186,186,184],0.652,[188,188,188,226,186,184,186,186,184],0.483,[188,184,195,228,186,184,186,186,184],0.947,[188,188,195,230,186,184,186,186,184],0.751,[188,184,200,232,186,184,186,186,184],1.047,[188,188,200,234,186,184,186,186,184],1.521,[188,184,205,236,186,184,186,186,184],0.852,[188,188,205,238,186,184,186,186,184],0.798,[188,184,210,240,186,184,186,186,184],0.241,[188,188,210,242,186,184,186,186,184],0.187,[188,184,215,244,186,184,186,186,184],0.245,[188,188,215,246,186,184,186,186,184],0.308,[195,184,184,248,186,184,186,186,184],0.347,[195,188,184,250,186,184,186,186,184],0.312,[195,184,188,252,186,184,186,186,184],0.147,[195,188,188,254,186,184,186,186,184],0.129,[195,184,195,256,186,184,186,186,184],0.127,[195,188,195,258,186,184,186,186,184],0.257,[195,184,200,260,186,184,186,186,184],0.462,[195,188,200,262,186,184,186,186,184],0.41,[195,184,205,264,186,184,186,186,184],0.272,[195,188,205,266,186,184,186,186,184],0.252,[195,184,210,268,186,184,186,186,184],0.139,[195,188,210,270,186,184,186,186,184],0.044,[195,184,215,272,186,184,186,186,184],0.152,[195,188,215,274,186,184,186,186,184],0.051,[200,184,184,276,186,184,186,186,184],0.174,[200,188,184,278,186,184,186,186,184],0.291,[200,184,188,280,186,184,186,186,184],0.058,[200,188,188,282,186,184,186,186,184],0.073,[200,184,195,284,186,184,186,186,184],0.061,[200,188,195,286,186,184,186,186,184],0.496,[200,184,200,288,186,184,186,186,184],0.202,[200,188,200,290,186,184,186,186,184],0.702,[200,184,205,292,186,184,186,186,184],0.068,[200,188,205,294,186,184,186,186,184],0.414,[200,184,210,296,186,184,186,186,184],0.055,[200,188,210,298,186,184,186,186,184],0.075,[200,184,215,300,186,184,186,186,184],0.05,[200,188,215,302,186,184,186,186,184],0.077,[],[305],"arXiv v1 Supp. Table 7",[],[],[309],"Tracking accuracy on Botanic Garden using Velodyne VLP-16 data; RPE and ATE over full transformations; units, statistic and alignment not stated; 'Ours' is the authors' improved SR-LIVO tracker without loop closure; arXiv v1 supplementary",{"slug":311,"group":312,"sourceId":5,"sourceLabel":6,"table":313,"selfRows":314,"metrics":315,"seqs":324,"entrants":338,"cells":349,"outcomes":442,"locators":443,"hardware":444,"wordings":445,"notes":446},"gslivm2025-table-1","gslivm2025:Table 1","Table 1",12,[316,320,322],{"label":317,"unit":318,"statistic":319,"alignment":48},"PSNR","dB","mean",{"label":321,"unit":48,"statistic":319,"alignment":48},"SSIM",{"label":323,"unit":48,"statistic":319,"alignment":48},"LPIPS",[325,329,333,336],{"dataset":326,"sequence":327,"environment":328},"R3LIVE dataset","hku campus seq 00","Livox Avia, handheld, HKU campus outdoor",{"dataset":330,"sequence":331,"environment":332},"FAST-LIVO dataset (row-to-dataset mapping inferred from caption order)","Visual Challenge","Livox Avia, handheld, campus",{"dataset":97,"sequence":334,"environment":335},"eee 02","Ouster-16, outdoor",{"dataset":101,"sequence":155,"environment":337},"Livox Avia, wheeled robot, botanic garden",[339,341,344,347],{"name":340,"methodId":115,"linkable":75,"proposed":75,"self":75},"Nerf-SLAM [27]",{"name":342,"methodId":343,"linkable":173,"proposed":75,"self":75},"MonoGS [21]","monogs2024",{"name":345,"methodId":346,"linkable":173,"proposed":75,"self":75},"3DGS [13]","kerbl2023_3dgs",{"name":348,"methodId":5,"linkable":173,"proposed":173,"self":173},"Ours",[350,352,353,355,357,359,361,363,365,367,369,371,373,375,377,379,381,383,384,386,388,390,392,394,396,398,400,402,404,406,407,409,411,413,415,417,419,421,422,424,426,428,430,432,434,436,438,440],[184,184,184,351,186,184,186,186,184],13.232,[184,188,184,262,186,184,186,186,184],[184,195,184,354,186,184,186,186,184],0.653,[184,184,188,356,186,184,186,186,184],12.981,[184,188,188,358,186,184,186,186,184],0.408,[184,195,188,360,186,184,186,186,184],0.592,[184,184,195,362,186,184,186,186,184],8.316,[184,188,195,364,186,184,186,186,184],0.32,[184,195,195,366,186,184,186,186,184],0.693,[184,184,200,368,186,184,186,186,184],9.79,[184,188,200,370,186,184,186,186,184],0.362,[184,195,200,372,186,184,186,186,184],0.75,[188,184,184,374,186,184,186,186,184],12.142,[188,188,184,376,186,184,186,186,184],0.368,[188,195,184,378,186,184,186,186,184],0.608,[188,184,188,380,186,184,186,186,184],13.478,[188,188,188,382,186,184,186,186,184],0.579,[188,195,188,294,186,184,186,186,184],[188,184,195,385,186,184,186,186,184],11.632,[188,188,195,387,186,184,186,186,184],0.407,[188,195,195,389,186,184,186,186,184],0.514,[188,184,200,391,186,184,186,186,184],14.563,[188,188,200,393,186,184,186,186,184],0.602,[188,195,200,395,186,184,186,186,184],0.406,[195,184,184,397,186,184,186,186,184],21.744,[195,188,184,399,186,184,186,186,184],0.719,[195,195,184,401,186,184,186,186,184],0.302,[195,184,188,403,186,184,186,186,184],18.552,[195,188,188,405,186,184,186,186,184],0.545,[195,195,188,213,186,184,186,186,184],[195,184,195,408,186,184,186,186,184],20.388,[195,188,195,410,186,184,186,186,184],0.686,[195,195,195,412,186,184,186,186,184],0.382,[195,184,200,414,186,184,186,186,184],22.167,[195,188,200,416,186,184,186,186,184],0.657,[195,195,200,418,186,184,186,186,184],0.38,[200,184,184,420,186,184,186,186,184],22.43,[200,188,184,399,186,184,186,186,184],[200,195,184,423,186,184,186,186,184],0.247,[200,184,188,425,186,184,186,186,184],21.806,[200,188,188,427,186,184,186,186,184],0.717,[200,195,188,429,186,184,186,186,184],0.289,[200,184,195,431,186,184,186,186,184],20.718,[200,188,195,433,186,184,186,186,184],0.7,[200,195,195,435,186,184,186,186,184],0.319,[200,184,200,437,186,184,186,186,184],21.123,[200,188,200,439,186,184,186,186,184],0.679,[200,195,200,441,186,184,186,186,184],0.258,[],[313],[],[],[447],"Rendering quality, mean over all observation images; reduced scenes of at most 100 frames and 5 min reconstruction; NeRF-SLAM, MonoGS and 3DGS given COLMAP poses and depth, GS-LIVM uses its own LIVO poses",{"slug":449,"group":450,"sourceId":5,"sourceLabel":6,"table":451,"selfRows":314,"metrics":452,"seqs":469,"entrants":476,"cells":478,"outcomes":503,"locators":504,"hardware":505,"wordings":507,"notes":508},"gslivm2025-table-2","gslivm2025:Table 2","Table 2",[453,456,459,463,465,467],{"label":454,"unit":455,"statistic":150,"alignment":48},"MT (s), DT = 202 s","s",{"label":457,"unit":458,"statistic":150,"alignment":48},"Count of 3D Gaussians","count",{"label":460,"unit":461,"statistic":462,"alignment":48},"Mem (Mb), maximum memory cost","Mb (as written; megabytes or megabits not specified)","max",{"label":464,"unit":455,"statistic":150,"alignment":48},"MT (s), DT = 162 s",{"label":466,"unit":455,"statistic":150,"alignment":48},"MT (s), DT = 321 s",{"label":468,"unit":455,"statistic":150,"alignment":48},"MT (s), DT = 611 s",[470,472,474,475],{"dataset":326,"sequence":327,"environment":471},"outdoor",{"dataset":473,"sequence":331,"environment":471},"FAST-LIVO dataset",{"dataset":97,"sequence":334,"environment":471},{"dataset":101,"sequence":155,"environment":471},[477],{"name":348,"methodId":5,"linkable":173,"proposed":173,"self":173},[479,481,483,485,487,489,491,493,495,497,499,501],[184,184,184,480,186,184,184,186,184],202,[184,188,184,482,186,184,184,186,184],1209666,[184,195,184,484,186,184,184,186,184],2495,[184,200,188,486,186,184,184,186,184],162,[184,188,188,488,186,184,184,186,184],353334,[184,195,188,490,186,184,184,186,184],1353,[184,205,195,492,186,184,184,186,184],321,[184,188,195,494,186,184,184,186,184],758213,[184,195,195,496,186,184,184,186,184],1523,[184,210,200,498,186,184,184,186,184],612,[184,188,200,500,186,184,184,186,184],2177464,[184,195,200,502,186,184,184,186,184],3492,[],[451],[506],"Intel Core i9-13900HX (5.50 GHz), 64 GB RAM, NVIDIA RTX 4060 Laptop 8 GB GPU",[],[509],"Mapping time (MT) against sequence duration (DT), number of 3D Gaussians and maximum GPU memory for the full sequence, ns = 3",{"slug":511,"group":512,"sourceId":5,"sourceLabel":6,"table":513,"selfRows":514,"metrics":515,"seqs":524,"entrants":531,"cells":533,"outcomes":549,"locators":550,"hardware":552,"wordings":553,"notes":554},"gslivm2025-supp-table-8","gslivm2025:Supp. Table 8","Supp. Table 8",8,[516,518,520,521,522],{"label":517,"unit":455,"statistic":150,"alignment":48},"MT (s), DT = 1170 s",{"label":519,"unit":461,"statistic":462,"alignment":48},"Mem (Mb)",{"label":317,"unit":318,"statistic":319,"alignment":48},{"label":321,"unit":48,"statistic":319,"alignment":48},{"label":523,"unit":455,"statistic":150,"alignment":48},"MT (s), DT = 1073 s",[525,529],{"dataset":526,"sequence":527,"environment":528},"R3LIVE or FAST-LIVO dataset (not stated)","hku main building","outdoor campus, Livox Avia",{"dataset":526,"sequence":530,"environment":528},"hkust campus 00",[532],{"name":348,"methodId":5,"linkable":173,"proposed":173,"self":173},[534,536,538,540,542,544,546,548],[184,184,184,535,186,184,184,186,184],1170,[184,188,184,537,186,184,184,186,184],4489,[184,195,184,539,186,184,186,186,184],15.234,[184,200,184,541,186,184,186,186,184],0.538,[184,205,188,543,186,184,184,186,184],1090,[184,188,188,545,186,184,184,186,184],5812,[184,195,188,547,186,184,186,186,184],15.124,[184,200,188,286,186,184,186,186,184],[],[551],"arXiv v1 Supp. Table 8",[506],[],[555],"Ultra-long sequences with nr = 2: mapping time vs duration, peak memory and rendering metrics; arXiv v1 supplementary",[557,562,570,575,581],{"group":558,"slug":559,"sourceLabel":6,"table":560,"selfRows":215,"datasets":561},"gslivm2025:Supp. Table 4","gslivm2025-supp-table-4","Supp. Table 4",[101,326],{"group":563,"slug":564,"sourceLabel":6,"table":565,"selfRows":210,"datasets":566},"gslivm2025:Supp. Table 5","gslivm2025-supp-table-5","Supp. Table 5",[101,567,568,569],"FAST-LIVO or R3LIVE dataset (not stated)","not stated","self-collected",{"group":571,"slug":572,"sourceLabel":6,"table":573,"selfRows":205,"datasets":574},"gslivm2025:ICCV Supp. Table 4","gslivm2025-iccv-supp-table-4","ICCV Supp. Table 4",[568],{"group":576,"slug":577,"sourceLabel":6,"table":578,"selfRows":195,"datasets":579},"gslivm2025:ICCV Supp. Table 5","gslivm2025-iccv-supp-table-5","ICCV Supp. Table 5",[580,326],"FAST-LIVO dataset (row-to-dataset mapping inferred from Table 1 caption order)",{"group":582,"slug":583,"sourceLabel":6,"table":584,"selfRows":188,"datasets":585},"gslivm2025:ICCV Supp. Table 6","gslivm2025-iccv-supp-table-6","ICCV Supp. Table 6",[568],1790510658233]