[{"data":1,"prerenderedAt":558},["ShallowReactive",2],{"method-zhu2025meshloam":3},{"method":4,"reference":58,"equipment":78,"figures":116,"results":158},{"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":24,"limitations":30,"sensors":36,"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},"zhu2025meshloam","Zhu et al., 2025","Mesh-LOAM","Mesh-LOAM: Real-Time Mesh-Based LiDAR Odometry and Mapping",2025,"recent","C12","odometry_with_local_mapping","Mesh-LOAM 以隱式移動最小平方（IMLS）函數估計 SDF，但讓體素被動接收周圍點的 SDF 增量（passive voxel），避免逐體素搜尋近鄰，使每次掃描只需走訪各點一次；體素存於 GPU 平行空間雜湊表，並以 marching cubes 分區擷取網格。位姿以點對網格（point-to-mesh）里程計估計。","Real-time LiDAR odometry and meshing using an IMLS-based SDF accumulated in passive voxels on a GPU spatial hash, marching-cubes extraction and point-to-mesh odometry.","full_text_reviewed","peer_reviewed_published","main_body","里程計在 Hilti 2021 的六條序列評估，其中僅 Cons2 屬資料集的施工現場環境（Helmberger et al. 2022 描述為大部分戶外、約 40 m x 80 m、未完成表面）；Cons2 的 ATE 為 0.083 m，SLAMesh 0.339 m、KISS-ICP 0.835 m、SuMa 1.642 m、FLOAM 11.515 m，Puma 失敗（正式版 Table III）。Hilti 2021 真值多為 3 自由度位置。網格精度只在 Mai City（模擬）與 Newer College 以真值位姿評估；施工環境的網格僅作定性展示（正式版 Fig. 8，arXiv 版 Fig. 10），未在工地量化驗證。",[20,21,22,23],"public_benchmark","simulation","completed_building","real_construction_site",[25,26,27,28,29],"Authors argue implicit reconstruction is more robust to noise than the explicit meshing used by SLAMesh and ImMesh (Sec. I).","On six Hilti 2021 sequences (Ouster OS0-64) ATE was lowest on Base1, Cons2 and Camp2 (0.165, 0.083, 0.113 m); SLAMesh was lower than Mesh-LOAM on RPG (0.165 m, the lowest) and Lab (0.048 m), SuMa had the lowest Lab value (0.045 m) although the table bolds SLAMesh, KISS-ICP was lowest on Base4 (0.119 m), and Puma failed on all six (VoR Table III).","KITTI 00-10 mean relative error 0.51% and 0.14 deg\u002F100 m, second to KISS-ICP at 0.50%, and mean ATE 2.3 m, the lowest of eight methods (VoR Tables I-II).","With ground-truth poses and 0.1 m voxels, F-score 97.4 (10 cm) on Mai City and 94.1 (20 cm) on Newer College, above VDBFusion, Puma, SHINE-Mapping and SLAMesh (VoR Table V).","Passive voxels cut the SDF map update from 8806.20 ms to 2.12 ms per frame on KITTI (VoR Table VI).",[31,32,33,34,35],"On KITTI, sequences 04-06 were worse than KISS-ICP, which the authors attribute to a 0.2 m search interval (Sec. IV-C).","Requires an NVIDIA GPU; implemented in CUDA; 2860 MB of GPU memory on KITTI 07, and mesh simplification to reduce memory is future work (Sec. IV-A, IV-F, V).","Hilti evaluation: caption gives ATE in m but the text says %, and the statistic and alignment are not reported (VoR Sec. IV-C, Table III).","KITTI baselines partly imported from published papers (only DLO, KISS-ICP and FLOAM re-run), so settings are not uniform (VoR Sec. IV-C).","Handheld data gives non-uniform coverage and blank mesh edges (Sec. IV-D); data association is the runtime bottleneck (Sec. IV-F); (inference) no loop-closure module is described.",[37],"3D LiDAR",[39,40,21],"vehicle","handheld","scan-to-mesh odometry minimising point-to-facet-plane residuals by Gauss-Newton on SE(3) for a relative correction applied to a constant-velocity pose prediction (Sec. III-B.3)","planar points (PCA curvature below 0.1) are transformed by a constant-velocity prediction and matched to mesh facets by nearest-neighbour search; a match is kept by point-to-facet distance and only if the absolute cosine similarity of point and facet normals exceeds 0.98 (Sec. III-B, IV-A)","discrete poses","not_reported (LiDAR-only pipeline; no motion-compensation step described in arXiv v1)","none described (odometry and mapping only)","none reported","sparse passive voxels (0.1 m) storing position, normal, IMLS-based SDF, weight and frame index, updated by hybrid distance and normal weights over a 3-voxel influence cube; GPU spatial hash with linear probing; height-adaptive voxel blocks with length and width set to 2 (unit not stated) for partitioned marching cubes; expired voxels converted to mesh and deleted to bound memory; marching cubes at dynamic intervals (Sec. III-C, III-D, IV-A)","none","triangle mesh","GPU-centred C++ and CUDA (Intel i7-9800X, RTX 2080 Ti 11 GB); on KITTI 07 per frame 4.85 ms preprocessing, 10.96 ms odometry, 2.68 ms meshing, 18.49 ms total (about 54 fps) with 442 MB CPU and 2860 MB GPU memory, versus 29.27 ms and 3014 MB for SLAMesh and 3307.50 ms and 5766 MB for Puma (VoR Table VIII, Sec. IV-F)",null,"not_verified",[54],{"relation":55,"title":56,"doi_or_url":57},"preprint","arXiv:2312.15630 (v1 2023-12-25)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.15630",{"id":5,"kind":59,"shortName":7,"title":8,"authors":60,"year":9,"venue":64,"venueType":65,"publisher":66,"volumeIssuePages":67,"doi":68,"arxivId":69,"url":57,"firstPublicDate":70,"publicationStatus":16,"metadataStatus":71,"fulltextStatus":15,"era":10,"classicReason":72,"codeUrl":51,"cluster":11,"topics":73,"mdpi":74,"verification":75,"label":6,"fulltextRoute":76,"versionRead":77,"addedByCensus":74},"method",[61,62,63],"Yanjin Zhu","Xin Zheng","Jianke Zhu","IEEE Transactions on Intelligent Vehicles","journal","IEEE","10(1):24-35","10.1109\u002Ftiv.2024.3409085","2312.15630","2023-12-25","metadata_verified","not_applicable",[11],false,"corrected","NTU institutional (Chrome)","IEEE T-IV version of record (10(1):24-35, January 2025; online 2024-06-04) read in Chrome on the NTU network ('Access provided by National Taiwan University'): HTML full text of all sections, and Tables I-VIII viewed as the publisher's table images; arXiv 2312.15630v1 (11 pp., CC BY 4.0) also read for comparison. The VoR adds DLO to Table I, a KITTI ATE table (II), SuMa, Puma and SLAMesh on Hilti (III), an ATE table on Mai City and Newer College (IV), SLAMesh in the mapping table (V), an active versus passive SDF ablation (VI) and a runtime and memory table against Puma and SLAMesh (VIII); results were extracted from the VoR",[79,85,89,97,102,106,111],{"category":80,"model":81,"canonical":81,"role":82,"dataset":51,"specs":83,"locator":84},"compute","Intel Core i7-9800X","compute for runtime","3.80 GHz; the method runs mainly on the GPU except for data transmission","Sec. IV-A",{"category":80,"model":86,"canonical":87,"role":82,"dataset":51,"specs":88,"locator":84},"NVIDIA GeForce RTX 2080Ti","NVIDIA Geforce RTX2080Ti","11 GB GPU RAM; the method runs mainly on the GPU",{"category":90,"model":91,"canonical":92,"role":93,"dataset":94,"specs":95,"locator":96},"lidar","Velodyne HDL-64E S2","Velodyne HDL-64E","dataset sensor","KITTI Odometry","KITTI odometry sequences 00-10, 23,201 scans","Sec. IV-B",{"category":90,"model":98,"canonical":98,"role":93,"dataset":99,"specs":100,"locator":101},"Ouster OS0-64","Hilti SLAM Challenge 2021","360 deg field of view, 10 Hz; only this sensor's data used","Sec. IV-B; Sec. IV-C; Table III (VoR)",{"category":103,"model":104,"canonical":104,"role":93,"dataset":99,"specs":105,"locator":96},"platform","handheld sensor platform (Hilti 2021)","records the data and provides millimetre-accurate ground truth; most sequences have 3-DoF ground truth",{"category":90,"model":107,"canonical":107,"role":93,"dataset":108,"specs":109,"locator":110},"virtual Velodyne HDL-64 LiDAR","Mai City","synthetic urban-like scans (Mai City)","Sec. IV-B; Table IV (VoR)",{"category":90,"model":112,"canonical":113,"role":93,"dataset":114,"specs":115,"locator":110},"Ouster OS-1","Ouster OS1","Newer College","multi-beam 3D LiDAR on a handheld device at Oxford; dataset provides a millimetre-accurate 3D map; NCD-QUAD sequence",[117,130,139,148],{"refId":5,"refLabel":6,"fig":118,"whatZh":119,"license":120,"licenseUrl":121,"sourceUrl":122,"src":123,"width":124,"height":125,"thumb":126,"thumbWidth":127,"thumbHeight":128,"modified":129},"Fig. 1 (arXiv v1)","KITTI 00 序列的里程計軌跡與大範圍網格地圖，全流程約 54 fps","CC BY 4.0 (arXiv v1; version of record © IEEE)","http:\u002F\u002Fcreativecommons.org\u002Flicenses\u002Fby\u002F4.0\u002F","https:\u002F\u002Farxiv.org\u002Fhtml\u002F2312.15630v1\u002Fpic\u002Fkitti0.png","\u002Ffigure-files\u002Fzhu2025meshloam\u002Ffig-1-arxiv-v1.webp",1117,1200,"\u002Ffigure-files\u002Fzhu2025meshloam\u002Ffig-1-arxiv-v1.thumb.webp",480,516,"converted to WebP",{"refId":5,"refLabel":6,"fig":131,"whatZh":132,"license":120,"licenseUrl":121,"sourceUrl":133,"src":134,"width":135,"height":136,"thumb":137,"thumbWidth":127,"thumbHeight":138,"modified":129},"Fig. 2 (arXiv v1)","系統總覽：PCA 法向量估計、增量體素網格化、平行空間雜湊與點對網格里程計","https:\u002F\u002Farxiv.org\u002Fhtml\u002F2312.15630v1\u002Fmain.png","\u002Ffigure-files\u002Fzhu2025meshloam\u002Ffig-2-arxiv-v1.webp",1330,521,"\u002Ffigure-files\u002Fzhu2025meshloam\u002Ffig-2-arxiv-v1.thumb.webp",188,{"refId":5,"refLabel":6,"fig":140,"whatZh":141,"license":120,"licenseUrl":121,"sourceUrl":142,"src":143,"width":144,"height":145,"thumb":146,"thumbWidth":127,"thumbHeight":147,"modified":129},"Fig. 10 (arXiv v1) = Fig. 8 (VoR)","Hilti cons2 施工環境的現場照片與網格重建結果","https:\u002F\u002Farxiv.org\u002Fhtml\u002F2312.15630v1\u002Fhilti_reconsturction5.png","\u002Ffigure-files\u002Fzhu2025meshloam\u002Ffig-10-arxiv-v1-fig-8-vor.webp",924,281,"\u002Ffigure-files\u002Fzhu2025meshloam\u002Ffig-10-arxiv-v1-fig-8-vor.thumb.webp",146,{"refId":5,"refLabel":6,"fig":149,"whatZh":150,"license":120,"licenseUrl":121,"sourceUrl":151,"src":152,"width":153,"height":154,"thumb":155,"thumbWidth":127,"thumbHeight":156,"modified":157},"Fig. 11 (arXiv v1)","Mai City 上 Mesh-LOAM、Puma、SHINE-Mapping 與 VDBFusion 的網格及有號距離誤差圖","https:\u002F\u002Farxiv.org\u002Fhtml\u002F2312.15630v1\u002Fcolor.png","\u002Ffigure-files\u002Fzhu2025meshloam\u002Ffig-11-arxiv-v1.webp",1400,532,"\u002Ffigure-files\u002Fzhu2025meshloam\u002Ffig-11-arxiv-v1.thumb.webp",182,"resized to at most 1400 px wide and converted to WebP",{"totalRows":159,"groupCount":160,"groups":161,"others":542},40,7,[162,314,367,480],{"slug":163,"group":164,"sourceId":5,"sourceLabel":6,"table":165,"selfRows":166,"metrics":167,"seqs":183,"entrants":188,"cells":204,"outcomes":307,"locators":308,"hardware":310,"wordings":311,"notes":312},"zhu2025meshloam-table-v","zhu2025meshloam:Table V","Table V",10,[168,172,174,176,179,181],{"label":169,"unit":170,"statistic":171,"alignment":48},"Comp. (cm), completion","cm","not_reported",{"label":173,"unit":170,"statistic":171,"alignment":48},"Acc. (cm), accuracy",{"label":175,"unit":170,"statistic":171,"alignment":48},"C-L1 (cm), Chamfer-L1 distance",{"label":177,"unit":178,"statistic":171,"alignment":48},"Comp.Ratio (%)","%",{"label":180,"unit":178,"statistic":171,"alignment":48},"F-score (10cm) (%)",{"label":182,"unit":178,"statistic":171,"alignment":48},"F-score (20cm) (%)",[184,186],{"dataset":108,"sequence":108,"environment":185},"simulated urban street",{"dataset":114,"sequence":171,"environment":187},"outdoor college (handheld)",[189,193,196,199,202],{"name":190,"methodId":191,"linkable":192,"proposed":74,"self":74},"VDB Fusion [28]","vizzo2022vdbfusion",true,{"name":194,"methodId":195,"linkable":192,"proposed":74,"self":74},"Puma [13]","vizzo2021puma",{"name":197,"methodId":198,"linkable":192,"proposed":74,"self":74},"SHINE-Mapping [30]","shinemapping2023",{"name":200,"methodId":201,"linkable":192,"proposed":74,"self":74},"SLAMesh [14]","ruan2023slamesh",{"name":203,"methodId":5,"linkable":192,"proposed":192,"self":192},"Ours",[205,209,212,215,218,221,223,224,226,228,231,233,235,237,239,241,243,245,247,249,251,253,255,257,259,261,262,264,266,268,270,272,274,276,278,280,282,284,286,288,290,292,293,295,297,299,301,302,304,306],[206,206,206,207,208,206,208,208,206],0,6.9,-1,[206,210,206,211,208,206,208,208,206],1,1.3,[206,213,206,214,208,206,208,208,206],2,4.5,[206,216,206,217,208,206,208,208,206],3,90.2,[206,219,206,220,208,206,208,208,206],4,94.1,[206,206,210,222,208,206,208,208,206],12,[206,210,210,207,208,206,208,208,206],[206,213,210,225,208,206,208,208,206],9.4,[206,216,210,227,208,206,208,208,206],91.3,[206,229,210,230,208,206,208,208,206],5,92.6,[210,206,206,232,208,206,208,208,206],32,[210,210,206,234,208,206,208,208,206],1.2,[210,213,206,236,208,206,208,208,206],16.9,[210,216,206,238,208,206,208,208,206],78.8,[210,219,206,240,208,206,208,208,206],87.3,[210,206,210,242,208,206,208,208,206],15.4,[210,210,210,244,208,206,208,208,206],7.7,[210,213,210,246,208,206,208,208,206],11.5,[210,216,210,248,208,206,208,208,206],89.9,[210,229,210,250,208,206,208,208,206],91.9,[213,206,206,252,208,206,208,208,206],3.2,[213,210,206,254,208,206,208,208,206],1.1,[213,213,206,256,208,206,208,208,206],2.9,[213,216,206,258,208,206,208,208,206],95.2,[213,219,206,260,208,206,208,208,206],95.9,[213,206,210,166,208,206,208,208,206],[213,210,210,263,208,206,208,208,206],6.7,[213,213,210,265,208,206,208,208,206],8.4,[213,216,210,267,208,206,208,208,206],93.6,[213,229,210,269,208,206,208,208,206],93.7,[216,206,206,271,208,206,208,208,206],7.5,[216,210,206,273,208,206,208,208,206],3.7,[216,213,206,275,208,206,208,208,206],6.1,[216,216,206,277,208,206,208,208,206],89.2,[216,219,206,279,208,206,208,208,206],90.6,[216,206,210,281,208,206,208,208,206],13.7,[216,210,210,283,208,206,208,208,206],11.4,[216,213,210,285,208,206,208,208,206],12.6,[216,216,210,287,208,206,208,208,206],83.5,[216,229,210,289,208,206,208,208,206],82.3,[219,206,206,291,208,206,208,208,206],2.5,[219,210,206,234,208,206,208,208,206],[219,213,206,294,208,206,208,208,206],2.4,[219,216,206,296,208,206,208,208,206],96.3,[219,219,206,298,208,206,208,208,206],97.4,[219,206,210,300,208,206,208,208,206],9.6,[219,210,210,263,208,206,208,208,206],[219,213,210,303,208,206,208,208,206],8.2,[219,216,210,305,208,206,208,208,206],94.2,[219,229,210,220,208,206,208,208,206],[],[309],"Table V (VoR)",[],[],[313],"Mesh quality with ground-truth poses for all methods, voxel size 0.1 m, settings of SHINE-Mapping; distances in cm; completion ratio and F-score in % at 10 cm (Mai City) and 20 cm (Newer College)",{"slug":315,"group":316,"sourceId":5,"sourceLabel":6,"table":317,"selfRows":166,"metrics":318,"seqs":330,"entrants":333,"cells":338,"outcomes":359,"locators":360,"hardware":362,"wordings":364,"notes":365},"zhu2025meshloam-table-vi","zhu2025meshloam:Table VI","Table VI",[319,322,324,326,328],{"label":320,"unit":321,"statistic":171,"alignment":48},"Preprocess (ms)","ms",{"label":323,"unit":321,"statistic":171,"alignment":48},"Odometry (ms)",{"label":325,"unit":321,"statistic":171,"alignment":48},"SDF map update (ms)",{"label":327,"unit":321,"statistic":171,"alignment":48},"Partitioned Meshing (ms)",{"label":329,"unit":321,"statistic":171,"alignment":48},"Total Time (ms)",[331],{"dataset":94,"sequence":171,"environment":332},"outdoor driving",[334,336],{"name":335,"methodId":5,"linkable":192,"proposed":192,"self":192},"Mesh-LOAM with passive SDF computational model",{"name":337,"methodId":5,"linkable":192,"proposed":74,"self":192},"Mesh-LOAM with active SDF computational model",[339,341,343,345,347,349,351,353,355,357],[206,206,206,340,208,206,206,208,206],4.85,[206,210,206,342,208,206,206,208,206],10.96,[206,213,206,344,208,206,206,208,206],2.12,[206,216,206,346,208,206,206,208,206],0.56,[206,219,206,348,208,206,206,208,206],18.49,[210,206,206,350,208,206,206,208,206],5.18,[210,210,206,352,208,206,206,208,206],11.62,[210,213,206,354,208,206,206,208,206],8806.2,[210,216,206,356,208,206,206,208,206],1.4,[210,219,206,358,208,206,206,208,206],8824.4,[],[361],"Table VI (VoR)",[363],"Intel Core i7-9800X at 3.80 GHz with NVIDIA GeForce RTX 2080Ti (11 GB); Mesh-LOAM mainly on GPU, Puma and SLAMesh CPU-based (Sec. IV-A, IV-F)",[],[366],"Ablation on KITTI odometry: per-frame computational cost (ms) of each module with the passive (proposed) versus active SDF estimation model; both GPU-accelerated",{"slug":368,"group":369,"sourceId":5,"sourceLabel":6,"table":370,"selfRows":371,"metrics":372,"seqs":376,"entrants":394,"cells":407,"outcomes":472,"locators":474,"hardware":476,"wordings":477,"notes":478},"zhu2025meshloam-table-iii","zhu2025meshloam:Table III","Table III",6,[373],{"label":374,"unit":375,"statistic":171,"alignment":171},"ATE (m)","m",[377,380,383,385,388,391],{"dataset":99,"sequence":378,"environment":379},"RPG","indoor (RPG)",{"dataset":99,"sequence":381,"environment":382},"Base1","basement",{"dataset":99,"sequence":384,"environment":382},"Base4",{"dataset":99,"sequence":386,"environment":387},"Lab","laboratory",{"dataset":99,"sequence":389,"environment":390},"Cons2","construction site (outdoor)",{"dataset":99,"sequence":392,"environment":393},"Camp2","campus (outdoor)",[395,398,401,404,405,406],{"name":396,"methodId":397,"linkable":192,"proposed":74,"self":74},"SuMa [8]","suma2018",{"name":399,"methodId":400,"linkable":192,"proposed":74,"self":74},"FLOAM [4]","floam2021",{"name":402,"methodId":403,"linkable":192,"proposed":74,"self":74},"KISS-ICP [5]","kissicp2023",{"name":194,"methodId":195,"linkable":192,"proposed":74,"self":74},{"name":200,"methodId":201,"linkable":192,"proposed":74,"self":74},{"name":203,"methodId":5,"linkable":192,"proposed":192,"self":192},[408,410,412,414,416,418,419,421,423,425,427,429,431,433,435,437,439,441,443,444,445,446,447,448,449,451,453,455,457,459,461,463,464,466,468,470],[206,206,206,409,208,206,208,208,206],0.262,[206,206,210,411,208,206,208,208,206],2.244,[206,206,213,413,208,206,208,208,206],0.286,[206,206,216,415,208,206,208,208,206],0.045,[206,206,219,417,208,206,208,208,206],1.642,[206,206,229,51,206,206,208,208,206],[210,206,206,420,208,206,208,208,206],2.775,[210,206,210,422,208,206,208,208,206],0.914,[210,206,213,424,208,206,208,208,206],0.287,[210,206,216,426,208,206,208,208,206],0.182,[210,206,219,428,208,206,208,208,206],11.515,[210,206,229,430,208,206,208,208,206],8.946,[213,206,206,432,208,206,208,208,206],0.187,[213,206,210,434,208,206,208,208,206],0.294,[213,206,213,436,208,206,208,208,206],0.119,[213,206,216,438,208,206,208,208,206],0.073,[213,206,219,440,208,206,208,208,206],0.835,[213,206,229,442,208,206,208,208,206],5.052,[216,206,206,51,206,206,208,208,206],[216,206,210,51,206,206,208,208,206],[216,206,213,51,206,206,208,208,206],[216,206,216,51,206,206,208,208,206],[216,206,219,51,206,206,208,208,206],[216,206,229,51,206,206,208,208,206],[219,206,206,450,208,206,208,208,206],0.165,[219,206,210,452,208,206,208,208,206],0.175,[219,206,213,454,208,206,208,208,206],0.33,[219,206,216,456,208,206,208,208,206],0.048,[219,206,219,458,208,206,208,208,206],0.339,[219,206,229,460,208,206,208,208,206],0.653,[229,206,206,462,208,206,208,208,206],0.173,[229,206,210,450,208,206,208,208,206],[229,206,213,465,208,206,208,208,206],0.267,[229,206,216,467,208,206,208,208,206],0.049,[229,206,219,469,208,206,208,208,206],0.083,[229,206,229,471,208,206,208,208,206],0.113,[473],"failed",[475],"Table III (VoR)",[],[],[479],"Hilti SLAM Challenge 2021, Ouster OS0-64 data only; all methods run by the authors with their own implementations; caption gives ATE in m while the text says %; most sequences have 3-DoF ground truth; 'x' = failed registration",{"slug":481,"group":482,"sourceId":5,"sourceLabel":6,"table":483,"selfRows":371,"metrics":484,"seqs":496,"entrants":500,"cells":504,"outcomes":535,"locators":536,"hardware":538,"wordings":539,"notes":540},"zhu2025meshloam-table-viii","zhu2025meshloam:Table VIII","Table VIII",[485,486,487,489,490,494],{"label":320,"unit":321,"statistic":171,"alignment":48},{"label":323,"unit":321,"statistic":171,"alignment":48},{"label":488,"unit":321,"statistic":171,"alignment":48},"Meshing (ms)",{"label":329,"unit":321,"statistic":171,"alignment":48},{"label":491,"unit":492,"statistic":493,"alignment":48},"CPU Memory (MB), peak","MB","max",{"label":495,"unit":492,"statistic":493,"alignment":48},"GPU Memory (MB), peak",[497],{"dataset":94,"sequence":498,"environment":499},"07","outdoor driving (urban)",[501,502,503],{"name":194,"methodId":195,"linkable":192,"proposed":74,"self":74},{"name":200,"methodId":201,"linkable":192,"proposed":74,"self":74},{"name":203,"methodId":5,"linkable":192,"proposed":192,"self":192},[505,507,509,511,513,515,516,517,519,521,523,525,526,527,528,530,531,533],[206,206,206,506,208,206,206,208,206],94,[206,210,206,508,208,206,206,208,206],1000,[206,213,206,510,208,206,206,208,206],2213.5,[206,216,206,512,208,206,206,208,206],3307.5,[206,219,206,514,208,206,206,208,206],5766,[206,229,206,206,208,206,206,208,206],[210,206,206,350,208,206,206,208,206],[210,210,206,518,208,206,206,208,206],9.78,[210,213,206,520,208,206,206,208,206],14.31,[210,216,206,522,208,206,206,208,206],29.27,[210,219,206,524,208,206,206,208,206],3014,[210,229,206,206,208,206,206,208,206],[213,206,206,340,208,206,206,208,206],[213,210,206,342,208,206,206,208,206],[213,213,206,529,208,206,206,208,206],2.68,[213,216,206,348,208,206,206,208,206],[213,219,206,532,208,206,206,208,206],442,[213,229,206,534,208,206,206,208,206],2860,[],[537],"Table VIII (VoR)",[363],[],[541],"KITTI sequence 07: per-frame computational time (ms) and peak memory (MB); Puma and SLAMesh are CPU-based; Mesh-LOAM allocates extra GPU memory for parallel operations",[543,548,553],{"group":544,"slug":545,"sourceLabel":6,"table":546,"selfRows":219,"datasets":547},"zhu2025meshloam:Table I","zhu2025meshloam-table-i","Table I",[94],{"group":549,"slug":550,"sourceLabel":6,"table":551,"selfRows":213,"datasets":552},"zhu2025meshloam:Table II","zhu2025meshloam-table-ii","Table II",[94],{"group":554,"slug":555,"sourceLabel":6,"table":556,"selfRows":213,"datasets":557},"zhu2025meshloam:Table IV","zhu2025meshloam-table-iv","Table IV",[108,114],1790510658932]