[{"data":1,"prerenderedAt":842},["ShallowReactive",2],{"method-nerfloam2023":3},{"method":4,"reference":54,"equipment":80,"figures":102,"results":103},{"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":26,"sensors":32,"platform":34,"estimator":37,"association":38,"timeModel":39,"deskew":40,"loopClosure":41,"globalOptimization":42,"mapRepresentation":43,"prior":44,"outputGeometry":45,"compute":46,"codeUrl":47,"codeLicense":48,"relatedVersions":49},"nerfloam2023","Deng et al., 2023","NeRF-LOAM","NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mapping",2023,"recent","C09","odometry_with_local_mapping","NeRF-LOAM 將 LiDAR 里程計與建圖都建立在稀疏八元樹體素嵌入加上共用解碼器的神經 SDF 上，以 SDF 誤差對位姿做梯度下降，並把地面與非地面點分開以抑制 Z 方向漂移。最後以關鍵掃描緩衝區精修地圖與位姿，再用 marching cubes 輸出網格。作者承認目前無法即時且沒有迴圈閉合。","LiDAR odometry and mapping on a neural SDF in sparse octree voxels, optimizing poses and embeddings jointly, then meshing.","full_text_reviewed","peer_reviewed_published","main_body","論文未在營建場域測試；資料為 MaiCity（合成）、Newer College（手持）、KITTI（車載）。",[20,21,22],"simulation","public_benchmark","independent_reference",[24,25],"Higher-quality mesh maps than learning-based and classical baselines on MaiCity and Newer College (Sec. 5.2; Sec. 6)","No pre-training required (abstract)",[27,28,29,30,31],"Not real-time; ray-map intersection is the bottleneck (Sec. 6)","No loop closure (Sec. 6)","Follow-up [pinslam2024] reports processing time growing with the number of scans (PIN-SLAM Sec. V-F2)","On KITTI sequences with loops the method cannot keep a consistent global map; loops cause overlapping meshes (Supp. A, Fig. 15; Supp. D)","Without ground separation the odometry fails on Newer College (Table 4)",[33],"3D LiDAR (MaiCity: noise-free synthetic 64-beam scans; Newer College: hand-carried LiDAR; KITTI; sensor models not named in the paper)",[35,36,20],"vehicle","handheld","gradient descent on SE(3) (Lie algebra) minimizing the SDF loss against the current implicit map, initialised by a constant motion model; the shared MLP is frozen after the first K scans to limit catastrophic forgetting; neural mapping jointly optimizes voxel embeddings and fine-tunes poses; final key-scan refinement of map and poses","neural SDF with ground\u002Fnon-ground separation of LiDAR points to limit Z drift","discrete poses","not_reported (Newer College used 'with motion distortion'; no deskewing described in sections read)","none (planned future work)","key-scan buffer refinement of map and poses at the end (not loop-based)","sparse octree voxels with neural embeddings and a shared 2-layer MLP decoding SDF","none (pre-training free)","dense mesh via marching cubes + refined scan poses","tested on an Intel Xeon CPU at 2.1 GHz with an NVIDIA Titan RTX (24 GB) (Sec. 5.5); not real-time with the unoptimized Python implementation, the ray and map intersection query being the bottleneck (Sec. 6); [pinslam2024] Table XVI reports 4.43 s per frame (0.2 Hz) on an NVIDIA A4000 over KITTI 00-10","https:\u002F\u002Fgithub.com\u002FJunyuanDeng\u002FNeRF-LOAM","MIT",[50],{"relation":51,"title":52,"doi_or_url":53},"preprint","arXiv:2303.10709","https:\u002F\u002Farxiv.org\u002Fabs\u002F2303.10709",{"id":5,"kind":55,"shortName":7,"title":8,"authors":56,"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":74,"codeUrl":47,"cluster":11,"topics":75,"mdpi":76,"verification":77,"label":6,"fulltextRoute":78,"versionRead":79,"addedByCensus":76},"method",[57,58,59,60,61,62,63,64],"Junyuan Deng","Qi Wu","Xieyuanli Chen","Songpengcheng Xia","Zhen Sun","Guoqing Liu","Wenxian Yu","Ling Pei","2023 IEEE\u002FCVF International Conference on Computer Vision (ICCV)","conference","IEEE","pp. 8184-8193","10.1109\u002Ficcv51070.2023.00755","2303.10709","https:\u002F\u002Fapi.crossref.org\u002Fworks\u002F10.1109\u002Ficcv51070.2023.00755","2023-03-19","metadata_verified","not_applicable",[11],false,"corrected","arXiv","arXiv v1 (2023-03-19, the only arXiv version) read in full including supplementary Sec. A to D; CVF open-access ICCV 2023 version also read: Tables 1 to 4, hardware sentence and limitation paragraph identical to arXiv v1; the CVF version adds author Qi Wu (8 authors)",[81,88,91,98],{"category":82,"model":83,"canonical":83,"role":84,"dataset":85,"specs":86,"locator":87},"compute","Intel Xeon CPU (2.1 GHz)","compute for runtime",null,"used for the voxel-size, processing-time and memory study","Sec. 5.5",{"category":82,"model":89,"canonical":89,"role":84,"dataset":85,"specs":90,"locator":87},"NVIDIA Titan RTX (24 GB)","24 GB memory",{"category":92,"model":93,"canonical":93,"role":94,"dataset":95,"specs":96,"locator":97},"lidar","64-beam LiDAR (simulated, noise-free)","dataset sensor","MaiCity","synthetic scans with a provided ground-truth map","Sec. 5.1",{"category":92,"model":99,"canonical":99,"role":94,"dataset":100,"specs":101,"locator":97},"not_reported (hand-carried LiDAR)","Newer College","hand-carried sequence at Oxford University with motion distortion; ground-truth trajectories and mesh provided by the dataset",[],{"totalRows":104,"groupCount":105,"groups":106,"others":812},78,9,[107,442,566,738],{"slug":108,"group":109,"sourceId":110,"sourceLabel":111,"table":112,"selfRows":113,"metrics":114,"seqs":126,"entrants":142,"cells":163,"outcomes":435,"locators":437,"hardware":438,"wordings":439,"notes":440},"livgs2025-table-ii","livgs2025:Table II","livgs2025","Xiao et al., 2025","Table II",18,[115,120,123],{"label":116,"unit":117,"statistic":118,"alignment":119},"t_rel (average translational RMSE drift)","%","RMSE","not_reported",{"label":121,"unit":122,"statistic":118,"alignment":119},"r_rel (average rotational RMSE drift)","deg\u002F100 m",{"label":124,"unit":125,"statistic":118,"alignment":119},"t_abs (ATE RMSE)","m",[127,131,133,135,137,139],{"dataset":128,"sequence":129,"environment":130},"NTU4DRadLM","cp","outdoor, low-speed segment (cp about 230 m; garden and nyl segments at least 220 m each), Livox Horizon",{"dataset":128,"sequence":132,"environment":130},"garden1",{"dataset":128,"sequence":134,"environment":130},"garden2",{"dataset":128,"sequence":136,"environment":130},"nyl1",{"dataset":128,"sequence":138,"environment":130},"nyl2",{"dataset":128,"sequence":140,"environment":141},"loop2","outdoor, human-driven vehicle, high speed, 300 frames over about 250 m, Livox Horizon",[143,145,148,151,154,157,159,161],{"name":7,"methodId":5,"linkable":144,"proposed":76,"self":144},true,{"name":146,"methodId":147,"linkable":76,"proposed":76,"self":76},"HDL-graph-SLAM","koide2019_hdlgraphslam",{"name":149,"methodId":150,"linkable":144,"proposed":76,"self":76},"ORB-SLAM3","orbslam3_2021",{"name":152,"methodId":153,"linkable":144,"proposed":76,"self":76},"SplaTAM","splatam2024",{"name":155,"methodId":156,"linkable":144,"proposed":76,"self":76},"MonoGS","monogs2024",{"name":158,"methodId":85,"linkable":76,"proposed":76,"self":76},"Gaussian-SLAM",{"name":160,"methodId":85,"linkable":76,"proposed":76,"self":76},"GS-ICP-SLAM",{"name":162,"methodId":110,"linkable":144,"proposed":144,"self":76},"Ours",[164,168,171,174,176,178,180,182,184,186,189,191,193,196,198,200,203,205,207,209,211,213,215,217,219,221,223,225,227,229,231,233,235,237,239,241,243,245,247,249,251,253,255,257,259,261,263,265,267,269,271,273,275,277,279,280,281,283,284,285,287,288,289,291,292,293,295,296,297,299,300,301,303,305,307,309,311,313,315,317,319,321,323,325,327,328,330,332,334,336,338,340,342,344,345,346,347,348,349,350,351,352,353,354,355,356,358,360,362,365,367,369,370,372,374,376,378,380,382,384,386,388,390,392,394,396,398,401,403,405,407,409,411,413,415,417,419,421,423,425,427,429,431,433],[165,165,165,166,167,165,167,167,165],0,2.943,-1,[165,169,165,170,167,165,167,167,165],1,9.644,[165,172,165,173,167,165,167,167,165],2,5.39,[165,165,169,175,167,165,167,167,165],1.182,[165,169,169,177,167,165,167,167,165],0.559,[165,172,169,179,167,165,167,167,165],0.54,[165,165,172,181,167,165,167,167,165],1.213,[165,169,172,183,167,165,167,167,165],0.707,[165,172,172,185,167,165,167,167,165],1.076,[165,165,187,188,167,165,167,167,165],3,1.371,[165,169,187,190,167,165,167,167,165],1.14,[165,172,187,192,167,165,167,167,165],3.504,[165,165,194,195,167,165,167,167,165],4,1.343,[165,169,194,197,167,165,167,167,165],1.73,[165,172,194,199,167,165,167,167,165],17.46,[165,165,201,202,167,165,167,167,165],5,1.442,[165,169,201,204,167,165,167,167,165],2.205,[165,172,201,206,167,165,167,167,165],1.785,[169,165,165,208,167,165,167,167,165],1.264,[169,169,165,210,167,165,167,167,165],1.553,[169,172,165,212,167,165,167,167,165],1.079,[169,165,169,214,167,165,167,167,165],1.874,[169,169,169,216,167,165,167,167,165],1.603,[169,172,169,218,167,165,167,167,165],1.478,[169,165,172,220,167,165,167,167,165],1.186,[169,169,172,222,167,165,167,167,165],0.88,[169,172,172,224,167,165,167,167,165],3.154,[169,165,187,226,167,165,167,167,165],1.737,[169,169,187,228,167,165,167,167,165],1.271,[169,172,187,230,167,165,167,167,165],2.266,[169,165,194,232,167,165,167,167,165],1.514,[169,169,194,234,167,165,167,167,165],1.835,[169,172,194,236,167,165,167,167,165],17.638,[169,165,201,238,167,165,167,167,165],1.436,[169,169,201,240,167,165,167,167,165],2.802,[169,172,201,242,167,165,167,167,165],0.593,[172,165,165,244,167,165,167,167,165],1.356,[172,169,165,246,167,165,167,167,165],1.992,[172,172,165,248,167,165,167,167,165],2.865,[172,165,169,250,167,165,167,167,165],1.173,[172,169,169,252,167,165,167,167,165],0.626,[172,172,169,254,167,165,167,167,165],0.529,[172,165,172,256,167,165,167,167,165],1.212,[172,169,172,258,167,165,167,167,165],0.772,[172,172,172,260,167,165,167,167,165],1.001,[172,165,187,262,167,165,167,167,165],1.342,[172,169,187,264,167,165,167,167,165],1.172,[172,172,187,266,167,165,167,167,165],19.528,[172,165,194,268,167,165,167,167,165],1.333,[172,169,194,270,167,165,167,167,165],1.736,[172,172,194,272,167,165,167,167,165],23.283,[172,165,201,274,167,165,167,167,165],1.403,[172,169,201,276,167,165,167,167,165],2.256,[172,172,201,278,167,165,167,167,165],0.952,[187,165,165,85,165,165,167,167,165],[187,169,165,85,165,165,167,167,165],[187,172,165,282,167,165,167,167,165],2.336,[187,165,169,85,165,165,167,167,165],[187,169,169,85,165,165,167,167,165],[187,172,169,286,167,165,167,167,165],0.979,[187,165,172,85,165,165,167,167,165],[187,169,172,85,165,165,167,167,165],[187,172,172,290,167,165,167,167,165],1.221,[187,165,187,85,165,165,167,167,165],[187,169,187,85,165,165,167,167,165],[187,172,187,294,167,165,167,167,165],12.332,[187,165,194,85,165,165,167,167,165],[187,169,194,85,165,165,167,167,165],[187,172,194,298,167,165,167,167,165],17.442,[187,165,201,85,165,165,167,167,165],[187,169,201,85,165,165,167,167,165],[187,172,201,302,167,165,167,167,165],2.692,[194,165,165,304,167,165,167,167,165],4.171,[194,169,165,306,167,165,167,167,165],3.472,[194,172,165,308,167,165,167,167,165],3.44,[194,165,169,310,167,165,167,167,165],1.179,[194,169,169,312,167,165,167,167,165],0.754,[194,172,169,314,167,165,167,167,165],0.664,[194,165,172,316,167,165,167,167,165],1.163,[194,169,172,318,167,165,167,167,165],0.765,[194,172,172,320,167,165,167,167,165],0.708,[194,165,187,322,167,165,167,167,165],1.382,[194,169,187,324,167,165,167,167,165],1.175,[194,172,187,326,167,165,167,167,165],9.595,[194,165,194,188,167,165,167,167,165],[194,169,194,329,167,165,167,167,165],1.701,[194,172,194,331,167,165,167,167,165],28.553,[194,165,201,333,167,165,167,167,165],7.375,[194,169,201,335,167,165,167,167,165],5.708,[194,172,201,337,167,165,167,167,165],15.357,[201,165,165,339,167,165,167,167,165],1.249,[201,169,165,341,167,165,167,167,165],3.047,[201,172,165,343,167,165,167,167,165],1.04,[201,165,169,85,165,165,167,167,165],[201,169,169,85,165,165,167,167,165],[201,172,169,85,165,165,167,167,165],[201,165,172,85,165,165,167,167,165],[201,169,172,85,165,165,167,167,165],[201,172,172,85,165,165,167,167,165],[201,165,187,85,165,165,167,167,165],[201,169,187,85,165,165,167,167,165],[201,172,187,85,165,165,167,167,165],[201,165,194,85,165,165,167,167,165],[201,169,194,85,165,165,167,167,165],[201,172,194,85,165,165,167,167,165],[201,165,201,357,167,165,167,167,165],1.399,[201,169,201,359,167,165,167,167,165],2.384,[201,172,201,361,167,165,167,167,165],1.136,[363,165,165,364,167,165,167,167,165],6,5.471,[363,169,165,366,167,165,167,167,165],4.041,[363,172,165,368,167,165,167,167,165],6.33,[363,165,169,339,167,165,167,167,165],[363,169,169,371,167,165,167,167,165],0.764,[363,172,169,373,167,165,167,167,165],2.082,[363,165,172,375,167,165,167,167,165],1.824,[363,169,172,377,167,165,167,167,165],1.316,[363,172,172,379,167,165,167,167,165],5.507,[363,165,187,381,167,165,167,167,165],1.662,[363,169,187,383,167,165,167,167,165],1.771,[363,172,187,385,167,165,167,167,165],23.331,[363,165,194,387,167,165,167,167,165],2.101,[363,169,194,389,167,165,167,167,165],1.07,[363,172,194,391,167,165,167,167,165],23.915,[363,165,201,393,167,165,167,167,165],3.236,[363,169,201,395,167,165,167,167,165],2.644,[363,172,201,397,167,165,167,167,165],13.819,[399,165,165,400,167,165,167,167,165],7,0.234,[399,169,165,402,167,165,167,167,165],1.216,[399,172,165,404,167,165,167,167,165],0.464,[399,165,169,406,167,165,167,167,165],1.183,[399,169,169,408,167,165,167,167,165],0.716,[399,172,169,410,167,165,167,167,165],0.366,[399,165,172,412,167,165,167,167,165],1.236,[399,169,172,414,167,165,167,167,165],0.962,[399,172,172,416,167,165,167,167,165],0.679,[399,165,187,418,167,165,167,167,165],1.24,[399,169,187,420,167,165,167,167,165],1.307,[399,172,187,422,167,165,167,167,165],0.58,[399,165,194,424,167,165,167,167,165],1.106,[399,169,194,426,167,165,167,167,165],1.369,[399,172,194,428,167,165,167,167,165],0.771,[399,165,201,430,167,165,167,167,165],1.393,[399,169,201,432,167,165,167,167,165],2.239,[399,172,201,434,167,165,167,167,165],0.843,[436],"not reported ('-' in table)",[112],[],[],[441],"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":443,"group":444,"sourceId":5,"sourceLabel":6,"table":445,"selfRows":446,"metrics":447,"seqs":459,"entrants":465,"cells":479,"outcomes":560,"locators":561,"hardware":562,"wordings":563,"notes":564},"nerfloam2023-table-1","nerfloam2023:Table 1","Table 1",16,[448,451,453,455,457],{"label":449,"unit":450,"statistic":119,"alignment":119},"Map. Acc.","cm (not stated in this table; identical values are labelled cm in PIN-SLAM Table XI)",{"label":452,"unit":450,"statistic":119,"alignment":119},"Map. Comp.",{"label":454,"unit":450,"statistic":119,"alignment":119},"C-l1 (Chamfer-L1)",{"label":456,"unit":117,"statistic":119,"alignment":119},"F-score (10cm)",{"label":458,"unit":117,"statistic":119,"alignment":119},"F-score (20cm)",[460,462],{"dataset":95,"sequence":119,"environment":461},"synthetic urban street (simulated 64-beam LiDAR)",{"dataset":100,"sequence":463,"environment":464},"not_reported (Newer College sequence not named; one of every five scans used)","outdoor campus, hand-carried LiDAR",[466,469,472,474,477],{"name":467,"methodId":468,"linkable":144,"proposed":76,"self":76},"SHINE [50] with KissICP poses","shinemapping2023",{"name":470,"methodId":471,"linkable":144,"proposed":76,"self":76},"Vdbfusion [37] with KissICP poses","vizzo2022vdbfusion",{"name":473,"methodId":5,"linkable":144,"proposed":144,"self":144},"Ours with KissICP poses",{"name":475,"methodId":476,"linkable":144,"proposed":76,"self":76},"Puma [36] with own odometry","vizzo2021puma",{"name":478,"methodId":5,"linkable":144,"proposed":144,"self":144},"Ours with own odometry",[480,482,484,486,488,490,492,494,496,498,500,502,504,506,508,510,512,514,516,518,520,522,524,526,528,530,532,534,536,538,540,542,544,546,548,550,552,554,556,558],[165,165,165,481,167,165,167,167,165],5.75,[165,169,165,483,167,165,167,167,165],38.45,[165,172,165,485,167,165,167,167,165],22.1,[165,187,165,487,167,165,167,167,165],67,[165,165,169,489,167,165,167,167,165],14.87,[165,169,169,491,167,165,167,167,165],20.02,[165,172,169,493,167,165,167,167,165],17.45,[165,194,169,495,167,165,167,167,165],68.85,[169,165,165,497,167,165,167,167,165],4.95,[169,169,165,499,167,165,167,167,165],46.79,[169,172,165,501,167,165,167,167,165],25.87,[169,187,165,503,167,165,167,167,165],68.15,[169,165,169,505,167,165,167,167,165],14.03,[169,169,169,507,167,165,167,167,165],25.46,[169,172,169,509,167,165,167,167,165],19.75,[169,194,169,511,167,165,167,167,165],69.5,[172,165,165,513,167,165,167,167,165],4.16,[172,169,165,515,167,165,167,167,165],37.2,[172,172,165,517,167,165,167,167,165],20.67,[172,187,165,519,167,165,167,167,165],73.31,[172,165,169,521,167,165,167,167,165],14.31,[172,169,169,523,167,165,167,167,165],24.39,[172,172,169,525,167,165,167,167,165],19.35,[172,194,169,527,167,165,167,167,165],68.7,[187,165,165,529,167,165,167,167,165],7.89,[187,169,165,531,167,165,167,167,165],9.14,[187,172,165,533,167,165,167,167,165],8.51,[187,187,165,535,167,165,167,167,165],68.04,[187,165,169,537,167,165,167,167,165],15.3,[187,169,169,539,167,165,167,167,165],71.91,[187,172,169,541,167,165,167,167,165],43.6,[187,194,169,543,167,165,167,167,165],57.27,[194,165,165,545,167,165,167,167,165],5.69,[194,169,165,547,167,165,167,167,165],11.23,[194,172,165,549,167,165,167,167,165],8.46,[194,187,165,551,167,165,167,167,165],77.26,[194,165,169,553,167,165,167,167,165],12.89,[194,169,169,555,167,165,167,167,165],22.21,[194,172,169,557,167,165,167,167,165],17.55,[194,194,169,559,167,165,167,167,165],74.37,[],[445],[],[],[565],"Simultaneous odometry and mapping; SHINE-Mapping and VDBFusion are fed KISS-ICP poses, NeRF-LOAM is shown with KISS-ICP poses and with its own odometry, Puma uses its own odometry; same voxel size for all; Newer College uses one of every five scans; accuracy, completion and Chamfer-L1 units not stated here (the same Newer College values are labelled cm in PIN-SLAM Table XI)",{"slug":567,"group":568,"sourceId":5,"sourceLabel":6,"table":569,"selfRows":446,"metrics":570,"seqs":578,"entrants":597,"cells":625,"outcomes":730,"locators":732,"hardware":734,"wordings":735,"notes":736},"nerfloam2023-table-5","nerfloam2023:Table 5","Table 5",[571,575],{"label":572,"unit":117,"statistic":573,"alignment":574},"t_rel (average translational RMSE, %)","mean","none",{"label":576,"unit":577,"statistic":573,"alignment":574},"r_rel (average rotational RMSE, deg\u002F100 m)","deg\u002F100m",[579,583,585,587,589,591,593,595],{"dataset":580,"sequence":581,"environment":582},"KITTI odometry","09","outdoor urban driving (car)",{"dataset":580,"sequence":584,"environment":582},"10",{"dataset":580,"sequence":586,"environment":582},"00",{"dataset":580,"sequence":588,"environment":582},"01",{"dataset":580,"sequence":590,"environment":582},"03",{"dataset":580,"sequence":592,"environment":582},"04",{"dataset":580,"sequence":594,"environment":582},"05",{"dataset":580,"sequence":596,"environment":582},"07",[598,601,604,607,610,612,614,617,619,622,624],{"name":599,"methodId":600,"linkable":144,"proposed":76,"self":76},"ICP-po2po [3]","besl1992icp",{"name":602,"methodId":603,"linkable":76,"proposed":76,"self":76},"ICP-po2pl [30]","rusinkiewicz2001variants",{"name":605,"methodId":606,"linkable":144,"proposed":76,"self":76},"GICP [31]","segal2009gicp",{"name":608,"methodId":609,"linkable":144,"proposed":76,"self":76},"SUMA [2]","suma2018",{"name":611,"methodId":476,"linkable":144,"proposed":76,"self":76},"PUMA(NN) [36]",{"name":613,"methodId":476,"linkable":144,"proposed":76,"self":76},"PUMA(RC) [36]",{"name":615,"methodId":616,"linkable":144,"proposed":76,"self":76},"DeLORA [26]","nubert2021delora",{"name":618,"methodId":85,"linkable":76,"proposed":76,"self":76},"DeepPCO [41]",{"name":620,"methodId":621,"linkable":144,"proposed":76,"self":76},"LONet [15]","lonet2019",{"name":623,"methodId":85,"linkable":76,"proposed":76,"self":76},"PWCLONet [39]",{"name":162,"methodId":5,"linkable":144,"proposed":144,"self":144},[626,628,630,632,634,636,638,640,642,644,646,648,650,652,654,656,658,660,662,664,666,668,670,672,674,676,678,680,682,683,684,686,687,690,691,692,694,696,698,700,701,704,705,707,709,711,713,715,716,718,720,721,722,724,726,728],[165,165,165,627,167,165,167,167,165],6.93,[165,169,165,629,167,165,167,167,165],2.89,[165,165,169,631,167,165,167,167,165],8.91,[165,169,169,633,167,165,167,167,165],4.47,[169,165,165,635,167,165,167,167,165],3.95,[169,169,165,637,167,165,167,167,165],1.71,[169,165,169,639,167,165,167,167,165],6.13,[169,169,169,641,167,165,167,167,165],2.6,[172,165,165,643,167,165,167,167,165],1.97,[172,169,165,645,167,165,167,167,165],0.77,[172,165,169,647,167,165,167,167,165],1.31,[172,169,169,649,167,165,167,167,165],0.62,[187,165,165,651,167,165,167,167,165],1.92,[187,169,165,653,167,165,167,167,165],0.78,[187,165,169,655,167,165,167,167,165],1.81,[187,169,169,657,167,165,167,167,165],0.97,[194,165,165,659,167,165,167,167,165],1.8,[194,169,165,661,167,165,167,167,165],0.82,[194,165,169,663,167,165,167,167,165],2.24,[194,169,169,665,167,165,167,167,165],1.67,[201,165,165,667,167,165,167,167,165],1.51,[201,169,165,669,167,165,167,167,165],0.66,[201,165,169,671,167,165,167,167,165],1.38,[201,169,169,673,167,165,167,167,165],0.84,[363,165,165,675,167,165,167,167,165],9.07,[363,169,165,677,167,165,167,167,165],3.14,[363,165,169,679,167,165,167,167,165],6.53,[363,169,169,681,167,165,167,167,165],4.22,[399,165,165,85,165,165,167,167,165],[399,169,165,85,165,165,167,167,165],[399,165,169,685,167,165,167,167,165],2.21,[399,169,169,665,167,165,167,167,165],[688,165,165,689,167,165,167,167,165],8,1.37,[688,169,165,422,167,165,167,167,165],[688,165,169,659,167,165,167,167,165],[688,169,169,693,167,165,167,167,165],0.93,[105,165,165,695,167,165,167,167,165],0.79,[105,169,165,697,167,165,167,167,165],0.35,[105,165,169,699,167,165,167,167,165],1.69,[105,169,169,649,167,165,167,167,165],[702,165,172,703,167,165,167,167,165],10,1.34,[702,169,172,179,167,165,167,167,165],[702,165,187,706,167,165,167,167,165],2.07,[702,169,187,708,167,165,167,167,165],0.52,[702,165,194,710,167,165,167,167,165],2.22,[702,169,194,712,167,165,167,167,165],1.57,[702,165,201,714,167,165,167,167,165],1.74,[702,169,201,169,167,165,167,167,165],[702,165,363,717,167,165,167,167,165],1.4,[702,169,363,719,167,165,167,167,165],0.65,[702,165,399,169,167,165,167,167,165],[702,169,399,719,167,165,167,167,165],[702,165,165,723,167,165,167,167,165],1.63,[702,169,165,725,167,165,167,167,165],0.57,[702,165,169,727,167,165,167,167,165],2.08,[702,169,169,729,167,165,167,167,165],0.69,[731],"not_reported ('-' in table)",[733],"Supp. Table 5",[],[],[737],"Supplementary KITTI odometry, average translational (%) and rotational (deg\u002F100 m) errors over 100 to 800 m subsequences; '*' marks results on training sequences of learning methods, '-' not provided",{"slug":739,"group":740,"sourceId":5,"sourceLabel":6,"table":741,"selfRows":688,"metrics":742,"seqs":748,"entrants":751,"cells":758,"outcomes":806,"locators":807,"hardware":808,"wordings":809,"notes":810},"nerfloam2023-table-2","nerfloam2023:Table 2","Table 2",[743,744,745,746],{"label":449,"unit":450,"statistic":119,"alignment":119},{"label":452,"unit":450,"statistic":119,"alignment":119},{"label":454,"unit":450,"statistic":119,"alignment":119},{"label":747,"unit":117,"statistic":119,"alignment":119},"F-score",[749,750],{"dataset":95,"sequence":119,"environment":461},{"dataset":100,"sequence":463,"environment":464},[752,754,756],{"name":753,"methodId":468,"linkable":144,"proposed":76,"self":76},"SHINE [50] with GT pose",{"name":755,"methodId":471,"linkable":144,"proposed":76,"self":76},"Vdbfusion [37] with GT pose",{"name":757,"methodId":5,"linkable":144,"proposed":144,"self":144},"Ours with GT pose",[759,761,763,765,767,769,771,773,775,777,779,781,783,785,787,789,791,793,795,796,798,800,802,804],[165,165,165,760,167,165,167,167,165],4.17,[165,169,165,762,167,165,167,167,165],5.3,[165,172,165,764,167,165,167,167,165],4.74,[165,187,165,766,167,165,167,167,165],89.67,[165,165,169,768,167,165,167,167,165],8.32,[165,169,169,770,167,165,167,167,165],14.36,[165,172,169,772,167,165,167,167,165],11.34,[165,187,169,774,167,165,167,167,165],90.65,[169,165,165,776,167,165,167,167,165],4.12,[169,169,165,778,167,165,167,167,165],8.01,[169,172,165,780,167,165,167,167,165],6.07,[169,187,165,782,167,165,167,167,165],90.16,[169,165,169,784,167,165,167,167,165],6.87,[169,169,169,786,167,165,167,167,165],18.37,[169,172,169,788,167,165,167,167,165],12.61,[169,187,169,790,167,165,167,167,165],89.96,[172,165,165,792,167,165,167,167,165],3.15,[172,169,165,794,167,165,167,167,165],4.84,[172,172,165,194,167,165,167,167,165],[172,187,165,797,167,165,167,167,165],92.96,[172,165,169,799,167,165,167,167,165],6.86,[172,169,169,801,167,165,167,167,165],15.59,[172,172,169,803,167,165,167,167,165],11.24,[172,187,169,805,167,165,167,167,165],91.83,[],[741],[],[],[811],"Mapping quality with ground-truth poses for all methods (pure mapping ability); voxel size 20 cm; caption states F-score in % with a 10 cm threshold",[813,819,824,830,835],{"group":814,"slug":815,"sourceLabel":816,"table":817,"selfRows":688,"datasets":818},"pinslam2024:Table XI","pinslam2024-table-xi","Pan et al., 2024","Table XI",[100],{"group":820,"slug":821,"sourceLabel":6,"table":822,"selfRows":194,"datasets":823},"nerfloam2023:Table 3","nerfloam2023-table-3","Table 3",[580,95,100],{"group":825,"slug":826,"sourceLabel":111,"table":827,"selfRows":187,"datasets":828},"livgs2025:Table IV","livgs2025-table-iv","Table IV",[829],"R3LIVE dataset",{"group":831,"slug":832,"sourceLabel":816,"table":833,"selfRows":187,"datasets":834},"pinslam2024:Table XVI","pinslam2024-table-xvi","Table XVI",[580],{"group":836,"slug":837,"sourceLabel":838,"table":817,"selfRows":172,"datasets":839},"tosi2026survey:Table XI","tosi2026survey-table-xi","Tosi et al., 2026",[840,841],"KITTI","Replica",1790510659151]