[{"data":1,"prerenderedAt":1083},["ShallowReactive",2],{"method-sumapp2019":3},{"method":4,"reference":58,"equipment":81,"figures":111,"results":152},{"id":5,"label":6,"shortName":7,"title":8,"year":9,"era":10,"cluster":11,"scope":12,"keyIdeaZh":13,"keyIdeaEn":14,"fulltextStatus":15,"publicationStatus":16,"recommendation":17,"constructionRelevance":18,"validationEnvironment":19,"strengths":21,"limitations":27,"sensors":34,"platform":36,"estimator":38,"association":39,"timeModel":40,"deskew":41,"loopClosure":42,"globalOptimization":43,"mapRepresentation":44,"prior":45,"outputGeometry":46,"compute":47,"codeUrl":48,"codeLicense":49,"relatedVersions":50},"sumapp2019","Chen et al., 2019","SuMa++","SuMa++: Efficient LiDAR-based Semantic SLAM",2019,"recent","C04","full_slam_with_global_correction","SuMa++ 在 SuMa 的面元建圖流程中加入 LiDAR 語意分割（RangeNet++，於球面投影影像上推論逐點類別），並以深度一致的洪水填充（flood-fill）修正物體邊界的標籤錯誤。更新地圖時若觀測類別與面元類別不一致，就降低該面元的穩定度，使移動物體逐漸被移除，同時保留停放車輛等靜態物體；ICP 殘差也依語意相容性加權以抑制離群值。","SuMa++ adds RangeNet++ point-wise semantics to SuMa, using label consistency to remove moving objects from the surfel map and to weight ICP residuals.","full_text_reviewed","peer_reviewed_published","background","not_reported（僅以 KITTI 驗證；（推論）工地機具與人員等動態物體會污染點雲，語意式動態過濾具參考價值，但需以工地類別重新訓練並驗證）。",[20],"public_benchmark",[22,23,24,25,26],"KITTI training average relative errors 0.29 deg\u002F100 m and 0.70%, vs 0.36\u002F0.83 for SuMa (Table II)","Consistent maps on KITTI raw road sequences with many consistently moving cars, where SuMa locks onto moving cars (Sec. IV-A, Fig. 6)","Naively removing all movable classes (SuMa_nomovable) diverges in urban scenes, while the proposed filtering keeps parked cars (Sec. IV-B)","KITTI raw road drives 30-41, which have no semantic labels: average 1.04 deg\u002F100 m and 1.46 % vs SuMa 1.35 deg\u002F100 m and 6.13 %; SuMa reached 26.8 %, 18.0 % and 15.6 % on drives 35, 40 and 41 (Table I, Sec. IV-A)","KITTI odometry test server: 1.06 % translational error vs 1.39 % for SuMa, both 0.0032 deg\u002Fm rotational (Sec. IV-B)",[28,29,30,31,32,33],"Relies on a network trained with KITTI\u002FSemanticKITTI labels (Sec. IV)","Cannot filter dynamic objects in the first observation; many moving objects in the first scan make it fail, so all movable classes are removed during initialization (Sec. IV-C)","Semantics not yet used for loop closure detection (Sec. V)","On KITTI training sequences its average translational error (0.70 %) is above the IMLS-SLAM value listed in the same table (0.55 %) (Table II)","(inference) Table II sequences 00-10 overlap the RangeNet++ training labels (00-10 except 08), so Table II is not a held-out test; the held-out evidence is Table I (unlabeled raw road drives) and the KITTI test-server result (Sec. IV-A, IV-B)","(inference) Class taxonomy and training domain (driving scenes) may not transfer to construction-site objects such as machinery, scaffolding and material piles; not tested",[35],"3D LiDAR (Velodyne HDL-64E S2 via KITTI)",[37],"vehicle (KITTI)","SuMa frame-to-model ICP (Gauss-Newton) with residual weights combining Huber, semantic compatibility and surfel stability; SuMa pose graph (Sec. III-B, III-F)","projective data association as in SuMa, with per-point labels from RangeNet++ refined by depth-aware flood-fill (Sec. III-C, III-D, III-F)","discrete scan poses","not_reported","SuMa loop closure and pose-graph optimization (Sec. III-B); semantics not used for loop closure (Sec. V)","pose graph as in SuMa","semantically labeled surfel map; semantic inconsistency penalizes surfel stability to remove moving objects (Sec. III-C, III-E)","trained semantic segmentation network (RangeNet++ trained on SemanticKITTI labels of KITTI sequences 00-10 except 08) (Sec. IV)","semantic surfel map with point-wise labels (Sec. III-C, Fig. 4)","Intel Xeon W-2123 (8 cores, 3.60 GHz, 16 GB RAM) with Nvidia Quadro P4000 (8 GB); RangeNet++ 75 ms and surfel mapping 48 ms on average per scan, at most 190 ms when integrating loop closures on KITTI sequence 00 (Sec. IV)","https:\u002F\u002Fgithub.com\u002FPRBonn\u002Fsemantic_suma","MIT (LICENSE file)",[51,55],{"relation":52,"title":53,"doi_or_url":54},"preprint","arXiv 2105.11320 (posted after the conference, comment: Accepted by IROS 2019)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2105.11320",{"relation":56,"title":57,"doi_or_url":48},"code_release","PRBonn\u002Fsemantic_suma",{"id":5,"kind":59,"shortName":7,"title":8,"authors":60,"year":9,"venue":67,"venueType":68,"publisher":69,"volumeIssuePages":70,"doi":71,"arxivId":72,"url":54,"firstPublicDate":73,"publicationStatus":16,"metadataStatus":74,"fulltextStatus":15,"era":10,"classicReason":75,"codeUrl":48,"cluster":11,"topics":76,"mdpi":77,"verification":78,"label":6,"fulltextRoute":79,"versionRead":80,"addedByCensus":77},"method",[61,62,63,64,65,66],"Xieyuanli Chen","Andres Milioto","Emanuele Palazzolo","Philippe Giguère","Jens Behley","Cyrill Stachniss","2019 IEEE\u002FRSJ International Conference on Intelligent Robots and Systems (IROS)","conference","IEEE","pp. 4530-4537","10.1109\u002Firos40897.2019.8967704","2105.11320","2019-11","metadata_verified","not_applicable",[11],false,"corrected","arXiv","arXiv 2105.11320v1 (posted 2021-05-24, author upload of the IROS 2019 paper, CC BY 4.0); Sec. IV-V of the IEEE version of record (doi 10.1109\u002FIROS40897.2019.8967704) also read on IEEE Xplore and found textually consistent",[82,90,96,102,108],{"category":83,"model":84,"canonical":85,"role":86,"dataset":87,"specs":88,"locator":89},"lidar","Velodyne HDL-64E S2","Velodyne HDL-64E","dataset sensor","KITTI (odometry benchmark and raw road drives)","point clouds recorded at 10 Hz (provided by KITTI)","Sec. IV",{"category":91,"model":92,"canonical":92,"role":93,"dataset":94,"specs":95,"locator":89},"gnss","inertial navigation system with GPS referenced to a base station (model not stated)","reference or ground truth","KITTI","source of KITTI ground-truth poses; described as accurate but often only locally consistent",{"category":97,"model":98,"canonical":98,"role":86,"dataset":99,"specs":100,"locator":101},"camera","front-view camera (model not stated)","KITTI raw","image shown only to illustrate the scene; not used by the method","Fig. 6(c)",{"category":103,"model":104,"canonical":104,"role":105,"dataset":106,"specs":107,"locator":89},"compute","Intel Xeon(R) W-2123","compute for runtime",null,"8 cores @3.60 GHz, 16 GB RAM",{"category":103,"model":109,"canonical":109,"role":105,"dataset":106,"specs":110,"locator":89},"Nvidia Quadro P4000","8 GB RAM",[112,125,135,144],{"refId":5,"refLabel":6,"fig":113,"whatZh":114,"license":115,"licenseUrl":116,"sourceUrl":117,"src":118,"width":119,"height":120,"thumb":121,"thumbWidth":122,"thumbHeight":123,"modified":124},"Fig. 1","以 SuMa++ 只用 LiDAR 掃描建立的 KITTI 語意面元地圖，面元顏色代表語意類別","CC BY 4.0","http:\u002F\u002Fcreativecommons.org\u002Flicenses\u002Fby\u002F4.0\u002F","https:\u002F\u002Farxiv.org\u002Fhtml\u002F2105.11320v1\u002Foverview.png","\u002Ffigure-files\u002Fsumapp2019\u002Ffig-1.webp",1089,1761,"\u002Ffigure-files\u002Fsumapp2019\u002Ffig-1.thumb.webp",480,776,"converted to WebP",{"refId":5,"refLabel":6,"fig":126,"whatZh":127,"license":115,"licenseUrl":116,"sourceUrl":128,"src":129,"width":130,"height":131,"thumb":132,"thumbWidth":122,"thumbHeight":133,"modified":134},"Fig. 2","系統流程圖：RangeNet++ 語意分割、多類別洪水填充修正、語意動態過濾與語意 ICP 嵌入 SuMa","https:\u002F\u002Farxiv.org\u002Fhtml\u002F2105.11320v1\u002Fpipeline.png","\u002Ffigure-files\u002Fsumapp2019\u002Ffig-2.webp",1400,486,"\u002Ffigure-files\u002Fsumapp2019\u002Ffig-2.thumb.webp",167,"resized to at most 1400 px wide and converted to WebP",{"refId":5,"refLabel":6,"fig":136,"whatZh":137,"license":115,"licenseUrl":116,"sourceUrl":138,"src":139,"width":140,"height":141,"thumb":142,"thumbWidth":122,"thumbHeight":143,"modified":124},"Fig. 4 (panel b)","動態過濾效果比較中 SuMa++ 的面元地圖，移動車輛被移除而停放車輛保留","https:\u002F\u002Farxiv.org\u002Fhtml\u002F2105.11320v1\u002Fdynamic_filter_suma++.png","\u002Ffigure-files\u002Fsumapp2019\u002Ffig-4-panel-b.webp",1086,1140,"\u002Ffigure-files\u002Fsumapp2019\u002Ffig-4-panel-b.thumb.webp",504,{"refId":5,"refLabel":6,"fig":145,"whatZh":146,"license":115,"licenseUrl":116,"sourceUrl":147,"src":148,"width":149,"height":150,"thumb":151,"thumbWidth":149,"thumbHeight":150,"modified":124},"Fig. 6 (panel b)","KITTI 公路序列中 SuMa++ 的點雲地圖，點色代表首次觀測時間，交通標誌一致對齊","https:\u002F\u002Farxiv.org\u002Fhtml\u002F2105.11320v1\u002Fseq20_suma++.png","\u002Ffigure-files\u002Fsumapp2019\u002Ffig-6-panel-b.webp",205,260,"\u002Ffigure-files\u002Fsumapp2019\u002Ffig-6-panel-b.thumb.webp",{"totalRows":153,"groupCount":154,"groups":155,"others":1021},116,15,[156,370,575,819],{"slug":157,"group":158,"sourceId":5,"sourceLabel":6,"table":159,"selfRows":160,"metrics":161,"seqs":170,"entrants":201,"cells":209,"outcomes":364,"locators":365,"hardware":366,"wordings":367,"notes":368},"sumapp2019-table-i","sumapp2019:Table I","Table I",26,[162,167],{"label":163,"unit":164,"statistic":165,"alignment":166},"relative rotational error","deg\u002F100 m","mean","none",{"label":168,"unit":169,"statistic":165,"alignment":166},"relative translational error","%",[171,175,177,179,182,184,186,188,190,192,194,196,198],{"dataset":172,"sequence":173,"environment":174},"KITTI raw (road category)","30","country",{"dataset":172,"sequence":176,"environment":174},"31",{"dataset":172,"sequence":178,"environment":174},"32",{"dataset":172,"sequence":180,"environment":181},"33","highway",{"dataset":172,"sequence":183,"environment":181},"34",{"dataset":172,"sequence":185,"environment":181},"35",{"dataset":172,"sequence":187,"environment":181},"36",{"dataset":172,"sequence":189,"environment":174},"37",{"dataset":172,"sequence":191,"environment":181},"38",{"dataset":172,"sequence":193,"environment":174},"39",{"dataset":172,"sequence":195,"environment":174},"40",{"dataset":172,"sequence":197,"environment":181},"41",{"dataset":172,"sequence":199,"environment":200},"Average","mixed",[202,206,208],{"name":203,"methodId":204,"linkable":205,"proposed":77,"self":77},"SuMa","suma2018",true,{"name":207,"methodId":106,"linkable":77,"proposed":77,"self":77},"SuMa_nomovable",{"name":7,"methodId":5,"linkable":205,"proposed":205,"self":205},[210,214,217,219,221,223,225,227,229,231,233,235,236,238,240,242,244,245,247,250,252,254,256,258,260,263,265,267,269,271,273,276,278,280,282,284,286,289,291,293,295,296,298,301,303,305,307,308,310,313,314,316,318,320,322,325,326,328,330,332,334,336,338,339,341,343,345,348,350,352,353,354,355,358,360,361,362,363],[211,211,211,212,213,211,213,213,211],0,0.38,-1,[211,215,211,216,213,211,213,213,211],1,0.96,[215,211,211,218,213,211,213,213,211],0.39,[215,215,211,220,213,211,213,213,211],0.97,[222,211,211,212,213,211,213,213,211],2,[222,215,211,224,213,211,213,213,211],0.9,[211,211,215,226,213,211,213,213,211],1.54,[211,215,215,228,213,211,213,213,211],2.02,[215,211,215,230,213,211,213,213,211],1.66,[215,215,215,232,213,211,213,213,211],2.13,[222,211,215,234,213,211,213,213,211],1.19,[222,215,215,228,213,211,213,213,211],[211,211,222,237,213,211,213,213,211],1.38,[211,215,222,239,213,211,213,213,211],1.7,[215,211,222,241,213,211,213,213,211],1.63,[215,215,222,243,213,211,213,213,211],1.76,[222,211,222,215,213,211,213,213,211],[222,215,222,246,213,211,213,213,211],1.57,[211,211,248,249,213,211,213,213,211],3,1.61,[211,215,248,251,213,211,213,213,211],1.79,[215,211,248,253,213,211,213,213,211],1.72,[215,215,248,255,213,211,213,213,211],1.8,[222,211,248,257,213,211,213,213,211],1.67,[222,215,248,259,213,211,213,213,211],1.87,[211,211,261,262,213,211,213,213,211],4,0.79,[211,215,261,264,213,211,213,213,211],1.17,[215,211,261,266,213,211,213,213,211],0.7,[215,215,261,268,213,211,213,213,211],1.14,[222,211,261,270,213,211,213,213,211],0.6,[222,215,261,272,213,211,213,213,211],1.09,[211,211,274,275,213,211,213,213,211],5,5.11,[211,215,274,277,213,211,213,213,211],26.8,[215,211,274,279,213,211,213,213,211],3.2,[215,215,274,281,213,211,213,213,211],1.22,[222,211,274,283,213,211,213,213,211],2.9,[222,215,274,285,213,211,213,213,211],1.11,[211,211,287,288,213,211,213,213,211],6,0.93,[211,215,287,290,213,211,213,213,211],1.31,[215,211,287,292,213,211,213,213,211],0.95,[215,215,287,294,213,211,213,213,211],1.3,[222,211,287,288,213,211,213,213,211],[222,215,287,297,213,211,213,213,211],1.4,[211,211,299,300,213,211,213,213,211],7,0.65,[211,215,299,302,213,211,213,213,211],1.51,[215,211,299,304,213,211,213,213,211],0.62,[215,215,299,306,213,211,213,213,211],1.36,[222,211,299,270,213,211,213,213,211],[222,215,299,309,213,211,213,213,211],1.48,[211,211,311,312,213,211,213,213,211],8,1.07,[211,215,311,230,213,211,213,213,211],[215,211,311,315,213,211,213,213,211],1.04,[215,215,311,317,213,211,213,213,211],1.46,[222,211,311,319,213,211,213,213,211],0.89,[222,215,311,321,213,211,213,213,211],1.42,[211,211,323,324,213,211,213,213,211],9,0.46,[211,215,323,315,213,211,213,213,211],[215,211,323,327,213,211,213,213,211],0.47,[215,215,323,329,213,211,213,213,211],0.98,[222,211,323,331,213,211,213,213,211],0.44,[222,215,323,333,213,211,213,213,211],1.05,[211,211,335,272,213,211,213,213,211],10,[211,215,335,337,213,211,213,213,211],18,[215,211,335,262,213,211,213,213,211],[215,215,335,340,213,211,213,213,211],1.92,[222,211,335,342,213,211,213,213,211],0.75,[222,215,335,344,213,211,213,213,211],1.95,[211,211,346,347,213,211,213,213,211],11,1.24,[211,215,346,349,213,211,213,213,211],15.6,[215,211,346,351,213,211,213,213,211],0.92,[215,215,346,317,213,211,213,213,211],[222,211,346,268,213,211,213,213,211],[222,215,346,257,213,211,213,213,211],[211,211,356,357,213,211,213,213,211],12,1.35,[211,215,356,359,213,211,213,213,211],6.13,[215,211,356,264,213,211,213,213,211],[215,215,356,317,213,211,213,213,211],[222,211,356,315,213,211,213,213,211],[222,215,356,317,213,211,213,213,211],[],[159],[],[],[369],"KITTI raw road-category drives 2011_09_26_drive_0015_sync to 2011_10_03_drive_0047_sync renamed 30-41; relative errors averaged over segments of 5 to 400 m (rot deg\u002F100 m, trans %); these drives have no semantic labels, so they are unseen by RangeNet++",{"slug":371,"group":372,"sourceId":5,"sourceLabel":6,"table":373,"selfRows":374,"metrics":375,"seqs":378,"entrants":405,"cells":414,"outcomes":568,"locators":570,"hardware":571,"wordings":572,"notes":573},"sumapp2019-table-ii","sumapp2019:Table II","Table II",24,[376,377],{"label":163,"unit":164,"statistic":165,"alignment":166},{"label":168,"unit":169,"statistic":165,"alignment":166},[379,383,385,387,389,391,394,396,398,400,402,404],{"dataset":380,"sequence":381,"environment":382},"KITTI odometry (training)","00","urban (loop)",{"dataset":380,"sequence":384,"environment":181},"01",{"dataset":380,"sequence":386,"environment":382},"02",{"dataset":380,"sequence":388,"environment":174},"03",{"dataset":380,"sequence":390,"environment":174},"04",{"dataset":380,"sequence":392,"environment":393},"05","country (loop)",{"dataset":380,"sequence":395,"environment":382},"06",{"dataset":380,"sequence":397,"environment":382},"07",{"dataset":380,"sequence":399,"environment":382},"08",{"dataset":380,"sequence":401,"environment":382},"09",{"dataset":380,"sequence":403,"environment":174},"10",{"dataset":380,"sequence":199,"environment":200},[406,407,408,409,411],{"name":203,"methodId":204,"linkable":205,"proposed":77,"self":77},{"name":207,"methodId":106,"linkable":77,"proposed":77,"self":77},{"name":7,"methodId":5,"linkable":205,"proposed":205,"self":205},{"name":410,"methodId":106,"linkable":77,"proposed":77,"self":77},"IMLS-SLAM [7]",{"name":412,"methodId":413,"linkable":205,"proposed":77,"self":77},"LOAM [40]","loam2017_auro",[415,417,419,421,423,425,427,429,431,433,434,436,437,438,440,442,444,446,448,450,452,454,455,457,458,459,461,463,465,466,467,468,470,472,473,475,476,477,478,480,482,484,486,488,490,491,493,495,496,498,499,500,501,503,504,505,506,507,508,509,511,513,514,515,517,518,519,521,523,525,527,529,531,532,533,534,536,537,538,540,542,543,545,546,548,550,552,553,554,556,558,560,562,564,565,566],[211,211,211,416,213,211,213,213,211],0.23,[211,215,211,418,213,211,213,213,211],0.68,[215,211,211,420,211,211,213,213,211],22,[215,215,211,422,211,211,213,213,211],58,[222,211,211,424,213,211,213,213,211],0.22,[222,215,211,426,213,211,213,213,211],0.64,[248,215,211,428,213,211,213,213,211],0.5,[261,215,211,430,213,211,213,213,211],0.78,[211,211,215,432,213,211,213,213,211],0.54,[211,215,215,239,213,211,213,213,211],[215,211,215,435,213,211,213,213,211],0.57,[215,215,215,239,213,211,213,213,211],[222,211,215,324,213,211,213,213,211],[222,215,215,439,213,211,213,213,211],1.6,[248,215,215,441,213,211,213,213,211],0.82,[261,215,215,443,213,211,213,213,211],1.43,[211,211,222,445,213,211,213,213,211],0.48,[211,215,222,447,213,211,213,213,211],1.2,[215,211,222,449,211,211,213,213,211],25,[215,215,222,451,211,211,213,213,211],63,[222,211,222,453,213,211,213,213,211],0.37,[222,215,222,215,213,211,213,213,211],[248,215,222,456,213,211,213,213,211],0.53,[261,215,222,351,213,211,213,213,211],[211,211,248,428,213,211,213,213,211],[211,215,248,460,213,211,213,213,211],0.74,[215,211,248,462,213,211,213,213,211],0.45,[215,215,248,464,213,211,213,213,211],0.67,[222,211,248,324,213,211,213,213,211],[222,215,248,464,213,211,213,213,211],[248,215,248,418,213,211,213,213,211],[261,215,248,469,213,211,213,213,211],0.86,[211,211,261,471,213,211,213,213,211],0.27,[211,215,261,331,213,211,213,213,211],[215,211,261,474,213,211,213,213,211],0.26,[215,215,261,453,213,211,213,213,211],[222,211,261,474,213,211,213,213,211],[222,215,261,453,213,211,213,213,211],[248,215,261,479,213,211,213,213,211],0.33,[261,215,261,481,213,211,213,213,211],0.71,[211,211,274,483,213,211,213,213,211],0.2,[211,215,274,485,213,211,213,213,211],0.43,[215,211,274,487,211,211,213,213,211],14,[215,215,274,489,211,211,213,213,211],36,[222,211,274,483,213,211,213,213,211],[222,215,274,492,213,211,213,213,211],0.4,[248,215,274,494,213,211,213,213,211],0.32,[261,215,274,435,213,211,213,213,211],[211,211,287,497,213,211,213,213,211],0.3,[211,215,287,432,213,211,213,213,211],[215,211,287,424,213,211,213,213,211],[215,215,287,327,213,211,213,213,211],[222,211,287,502,213,211,213,213,211],0.21,[222,215,287,324,213,211,213,213,211],[248,215,287,479,213,211,213,213,211],[261,215,287,300,213,211,213,213,211],[211,211,299,432,213,211,213,213,211],[211,215,299,460,213,211,213,213,211],[215,211,299,502,213,211,213,213,211],[215,215,299,510,213,211,213,213,211],0.34,[222,211,299,512,213,211,213,213,211],0.19,[222,215,299,510,213,211,213,213,211],[248,215,299,479,213,211,213,213,211],[261,215,299,516,213,211,213,213,211],0.63,[211,211,311,212,213,211,213,213,211],[211,215,311,447,213,211,213,213,211],[215,211,311,520,211,211,213,213,211],13,[215,215,311,522,211,211,213,213,211],32,[222,211,311,524,213,211,213,213,211],0.35,[222,215,311,526,213,211,213,213,211],1.1,[248,215,311,528,213,211,213,213,211],0.8,[261,215,311,530,213,211,213,213,211],1.12,[211,211,323,424,213,211,213,213,211],[211,215,323,304,213,211,213,213,211],[215,211,323,520,211,211,213,213,211],[215,215,323,535,211,211,213,213,211],45,[222,211,323,416,213,211,213,213,211],[222,215,323,327,213,211,213,213,211],[248,215,323,539,213,211,213,213,211],0.55,[261,215,323,541,213,211,213,213,211],0.77,[211,211,335,494,213,211,213,213,211],[211,215,335,544,213,211,213,213,211],0.72,[215,211,335,356,211,211,213,213,211],[215,215,335,547,211,211,213,213,211],19,[222,211,335,549,213,211,213,213,211],0.28,[222,215,335,551,213,211,213,213,211],0.66,[248,215,335,456,213,211,213,213,211],[261,215,335,262,213,211,213,213,211],[211,211,346,555,213,211,213,213,211],0.36,[211,215,346,557,213,211,213,213,211],0.83,[215,211,346,559,213,211,213,213,211],23.3,[215,215,346,561,213,211,213,213,211],9.24,[222,211,346,563,213,211,213,213,211],0.29,[222,215,346,266,213,211,213,213,211],[248,215,346,539,213,211,213,213,211],[261,215,346,567,213,211,213,213,211],0.84,[569],"(inference) diverged: authors state SuMa_nomovable diverges, particularly in urban scenes; per-sequence divergence not labelled in the paper",[373],[],[],[574],"KITTI odometry training sequences 00-10; relative errors averaged over 100 to 800 m segments (rot deg\u002F100 m, trans %); asterisked sequences 00, 02, 05-09 contain loops; RangeNet++ was trained on labels of 00-10 except 08, so this table is not held out; IMLS-SLAM and LOAM rows give translation only and their source is not stated; SuMa_nomovable Average printed as 23.3\u002F9.24, which looks swapped relative to its per-sequence values (reviewer arithmetic), recorded as printed",{"slug":576,"group":577,"sourceId":578,"sourceLabel":579,"table":373,"selfRows":580,"metrics":581,"seqs":590,"entrants":611,"cells":646,"outcomes":811,"locators":812,"hardware":813,"wordings":816,"notes":817},"mulls2021-table-ii","mulls2021:Table II","mulls2021","Pan et al., 2021",16,[582,584,587],{"label":583,"unit":169,"statistic":165,"alignment":41},"ATE [%] (average translation error)",{"label":585,"unit":586,"statistic":165,"alignment":41},"ARE [deg\u002F100m] (average rotation error)","deg\u002F100m",{"label":588,"unit":589,"statistic":41,"alignment":166},"time (s)\u002Fframe","s",[591,594,595,596,597,598,599,600,601,602,603,604,607,609],{"dataset":592,"sequence":381,"environment":593},"KITTI odometry","urban",{"dataset":592,"sequence":384,"environment":181},{"dataset":592,"sequence":386,"environment":174},{"dataset":592,"sequence":388,"environment":174},{"dataset":592,"sequence":390,"environment":174},{"dataset":592,"sequence":392,"environment":174},{"dataset":592,"sequence":395,"environment":593},{"dataset":592,"sequence":397,"environment":593},{"dataset":592,"sequence":399,"environment":593},{"dataset":592,"sequence":401,"environment":174},{"dataset":592,"sequence":403,"environment":174},{"dataset":592,"sequence":605,"environment":606},"00-10 mean","urban, highway, country",{"dataset":592,"sequence":608,"environment":606},"11-21 mean (online test set)",{"dataset":592,"sequence":610,"environment":606},"per frame",[612,615,617,619,621,623,625,627,630,632,634,636,638,640,642,644],{"name":613,"methodId":614,"linkable":205,"proposed":77,"self":77},"LOAM [10]","loam2014",{"name":616,"methodId":106,"linkable":77,"proposed":77,"self":77},"IMLS-SLAM [11]",{"name":618,"methodId":106,"linkable":77,"proposed":77,"self":77},"MC2SLAM [13]",{"name":620,"methodId":106,"linkable":77,"proposed":77,"self":77},"S4-SLAM [26]*",{"name":622,"methodId":106,"linkable":77,"proposed":77,"self":77},"PSF-LO [27]",{"name":624,"methodId":5,"linkable":205,"proposed":77,"self":205},"SUMA++ [16]*",{"name":626,"methodId":106,"linkable":77,"proposed":77,"self":77},"LiTAMIN2 [51]*",{"name":628,"methodId":629,"linkable":205,"proposed":77,"self":77},"LO-Net [18]","lonet2019",{"name":631,"methodId":106,"linkable":77,"proposed":77,"self":77},"FALO [25]",{"name":633,"methodId":106,"linkable":77,"proposed":77,"self":77},"LoDoNet [28]",{"name":635,"methodId":578,"linkable":205,"proposed":205,"self":77},"MULLS-LO(mc)",{"name":637,"methodId":578,"linkable":205,"proposed":205,"self":77},"MULLS-SLAM(mc)*",{"name":639,"methodId":578,"linkable":205,"proposed":205,"self":77},"MULLS-LO(s1)",{"name":641,"methodId":578,"linkable":205,"proposed":205,"self":77},"MULLS-SLAM(m1)*",{"name":643,"methodId":578,"linkable":205,"proposed":205,"self":77},"MULLS-SLAM(m5)*",{"name":645,"methodId":578,"linkable":205,"proposed":205,"self":77},"MULLS-SLAM(s5m5)*",[647,648,649,650,651,652,653,654,655,656,657,658,659,660,662,664,665,666,667,668,669,670,671,672,673,674,675,677,679,681,683,685,686,687,688,689,690,692,693,694,695,696,697,698,700,701,702,703,704,705,706,707,708,709,710,711,712,713,714,715,716,717,718,719,720,721,722,724,725,726,728,729,731,732,733,735,737,739,740,741,742,744,745,746,747,749,751,752,753,754,755,756,758,759,760,761,762,764,765,766,768,769,770,772,773,774,775,776,777,779,780,781,782,783,784,785,786,787,788,789,790,791,792,793,795,797,799,800,802,804,805,806,808,809,810],[211,211,211,430,213,211,213,213,211],[211,211,215,443,213,211,213,213,211],[211,211,222,351,213,211,213,213,211],[211,211,248,469,213,211,213,213,211],[211,211,261,481,213,211,213,213,211],[211,211,274,435,213,211,213,213,211],[211,211,287,300,213,211,213,213,211],[211,211,299,516,213,211,213,213,211],[211,211,311,530,213,211,213,213,211],[211,211,323,541,213,211,213,213,211],[211,211,335,262,213,211,213,213,211],[211,211,346,567,213,211,213,213,211],[211,211,356,539,213,211,213,213,211],[211,215,356,661,213,211,213,213,211],0.13,[211,222,520,663,213,211,211,213,211],0.1,[215,211,211,428,213,211,213,213,211],[215,211,215,441,213,211,213,213,211],[215,211,222,456,213,211,213,213,211],[215,211,248,418,213,211,213,213,211],[215,211,261,479,213,211,213,213,211],[215,211,274,494,213,211,213,213,211],[215,211,287,479,213,211,213,213,211],[215,211,299,479,213,211,213,213,211],[215,211,311,528,213,211,213,213,211],[215,211,323,539,213,211,213,213,211],[215,211,335,456,213,211,213,213,211],[215,211,346,676,213,211,213,213,211],0.52,[215,211,356,678,213,211,213,213,211],0.69,[215,215,356,680,213,211,213,213,211],0.18,[215,222,520,682,213,211,211,213,211],1.25,[222,211,211,684,213,211,213,213,211],0.51,[222,211,215,262,213,211,213,213,211],[222,211,222,432,213,211,213,213,211],[222,211,248,300,213,211,213,213,211],[222,211,261,331,213,211,213,213,211],[222,211,274,471,213,211,213,213,211],[222,211,287,691,213,211,213,213,211],0.31,[222,211,299,510,213,211,213,213,211],[222,211,311,567,213,211,213,213,211],[222,211,323,324,213,211,213,213,211],[222,211,335,676,213,211,213,213,211],[222,211,346,676,213,211,213,213,211],[222,211,356,678,213,211,213,213,211],[222,215,356,699,213,211,213,213,211],0.16,[222,222,520,663,213,211,211,213,211],[248,211,346,351,213,211,213,213,211],[248,211,356,288,213,211,213,213,211],[248,215,356,212,213,211,213,213,211],[248,222,520,483,213,211,211,213,211],[261,211,346,460,213,211,213,213,211],[261,211,356,441,213,211,213,213,211],[261,215,356,494,213,211,213,213,211],[261,222,520,483,213,211,211,213,211],[274,211,211,426,213,211,213,213,211],[274,211,215,439,213,211,213,213,211],[274,211,222,215,213,211,213,213,211],[274,211,248,464,213,211,213,213,211],[274,211,261,453,213,211,213,213,211],[274,211,274,492,213,211,213,213,211],[274,211,287,324,213,211,213,213,211],[274,211,299,510,213,211,213,213,211],[274,211,311,526,213,211,213,213,211],[274,211,323,327,213,211,213,213,211],[274,211,335,551,213,211,213,213,211],[274,211,346,266,213,211,213,213,211],[274,215,346,563,213,211,213,213,211],[274,211,356,723,213,211,213,213,211],1.06,[274,215,356,510,213,211,213,213,211],[274,222,520,663,213,211,211,213,211],[287,211,346,727,213,211,213,213,211],0.85,[287,215,346,479,213,211,213,213,211],[287,222,520,730,213,211,211,213,211],0.01,[299,211,211,430,213,211,213,213,211],[299,211,215,321,213,211,213,213,211],[299,211,222,734,213,211,213,213,211],1.01,[299,211,248,736,213,211,213,213,211],0.73,[299,211,261,738,213,211,213,213,211],0.56,[299,211,274,304,213,211,213,213,211],[299,211,287,539,213,211,213,213,211],[299,211,299,738,213,211,213,213,211],[299,211,311,743,213,211,213,213,211],1.08,[299,211,323,541,213,211,213,213,211],[299,211,335,351,213,211,213,213,211],[299,211,346,557,213,211,213,213,211],[299,215,346,748,213,211,213,213,211],0.42,[299,211,356,750,213,211,213,213,211],1.75,[299,215,356,262,213,211,213,213,211],[299,222,520,663,213,211,211,213,211],[311,211,346,215,213,211,213,213,211],[311,215,346,218,213,211,213,213,211],[311,222,520,663,213,211,211,213,211],[323,211,346,757,213,211,213,213,211],1.27,[323,215,346,551,213,211,213,213,211],[335,211,211,684,213,211,213,213,211],[335,211,215,304,213,211,213,213,211],[335,211,222,539,213,211,213,213,211],[335,211,248,763,213,211,213,213,211],0.61,[335,211,261,524,213,211,213,213,211],[335,211,274,549,213,211,213,213,211],[335,211,287,767,213,211,213,213,211],0.24,[335,211,299,563,213,211,213,213,211],[335,211,311,528,213,211,213,213,211],[335,211,323,771,213,211,213,213,211],0.49,[335,211,335,763,213,211,213,213,211],[335,211,346,771,213,211,213,213,211],[335,215,346,699,213,211,213,213,211],[335,211,356,300,213,211,213,213,211],[335,215,356,512,213,211,213,213,211],[335,222,520,778,213,211,215,213,211],0.08,[346,211,211,432,213,211,213,213,211],[346,211,215,304,213,211,213,213,211],[346,211,222,678,213,211,213,213,211],[346,211,248,763,213,211,213,213,211],[346,211,261,524,213,211,213,213,211],[346,211,274,563,213,211,213,213,211],[346,211,287,563,213,211,213,213,211],[346,211,299,471,213,211,213,213,211],[346,211,311,557,213,211,213,213,211],[346,211,323,684,213,211,213,213,211],[346,211,335,763,213,211,213,213,211],[346,211,346,676,213,211,213,213,211],[346,215,346,661,213,211,213,213,211],[346,222,520,663,213,211,215,213,211],[356,211,346,794,213,211,213,213,211],2.57,[356,215,346,796,213,211,213,213,211],1.03,[356,222,520,798,213,211,215,213,211],0.03,[520,211,346,541,213,211,213,213,211],[520,215,346,801,213,211,213,213,211],0.25,[520,222,520,803,213,211,215,213,211],0.05,[487,211,346,270,213,211,213,213,211],[487,215,346,680,213,211,213,213,211],[487,222,520,807,213,211,215,213,211],0.07,[154,211,346,763,213,211,213,213,211],[154,215,346,680,213,211,213,213,211],[154,222,520,778,213,211,215,213,211],[],[373],[814,815],"not_reported (value taken from original paper or KITTI leaderboard)","Intel Core i7-7700HQ @2.80GHz",[],[818],"KITTI odometry ATE [%] and ARE [deg\u002F100m], averaged over 100-800 m segments; baseline values from original papers and KITTI leaderboard; * = with loop closure; time in s per frame",{"slug":820,"group":821,"sourceId":822,"sourceLabel":823,"table":373,"selfRows":520,"metrics":824,"seqs":829,"entrants":844,"cells":865,"outcomes":1013,"locators":1015,"hardware":1016,"wordings":1017,"notes":1018},"ruan2023slamesh-table-ii","ruan2023slamesh:Table II","ruan2023slamesh","Ruan et al., 2023",[825,827],{"label":826,"unit":169,"statistic":165,"alignment":41},"relative translation error (%)",{"label":828,"unit":586,"statistic":165,"alignment":41},"relative rotation error (deg\u002F100m)",[830,832,833,834,835,836,837,838,839,840,841,842],{"dataset":592,"sequence":381,"environment":831},"urban, country and highway driving",{"dataset":592,"sequence":384,"environment":831},{"dataset":592,"sequence":386,"environment":831},{"dataset":592,"sequence":388,"environment":831},{"dataset":592,"sequence":390,"environment":831},{"dataset":592,"sequence":392,"environment":831},{"dataset":592,"sequence":395,"environment":831},{"dataset":592,"sequence":397,"environment":831},{"dataset":592,"sequence":399,"environment":831},{"dataset":592,"sequence":401,"environment":831},{"dataset":592,"sequence":403,"environment":831},{"dataset":592,"sequence":843,"environment":831},"Mean",[845,847,850,852,854,856,859,861,863],{"name":846,"methodId":614,"linkable":205,"proposed":77,"self":77},"LOAM",{"name":848,"methodId":849,"linkable":205,"proposed":77,"self":77},"A-LOAM","aloam_software",{"name":851,"methodId":204,"linkable":205,"proposed":77,"self":77},"Suma",{"name":853,"methodId":5,"linkable":205,"proposed":77,"self":205},"Suma++",{"name":855,"methodId":106,"linkable":77,"proposed":77,"self":77},"Litamin2",{"name":857,"methodId":858,"linkable":205,"proposed":77,"self":77},"Puma","vizzo2021puma",{"name":860,"methodId":822,"linkable":205,"proposed":205,"self":77},"SLAMesh (Ours) Full",{"name":862,"methodId":822,"linkable":205,"proposed":205,"self":77},"SLAMesh w\u002Fo Comb.",{"name":864,"methodId":822,"linkable":205,"proposed":205,"self":77},"SLAMesh w\u002Fo P2Mesh",[866,867,868,869,870,871,872,873,874,875,876,877,879,880,881,883,885,886,887,888,889,890,891,892,894,896,898,899,900,901,902,903,904,905,906,907,908,909,911,913,914,915,916,917,918,919,920,921,922,923,924,926,928,929,931,932,933,934,935,937,938,939,940,941,943,945,946,948,950,951,952,953,955,956,958,959,960,962,964,965,966,967,968,969,970,971,972,974,975,976,978,980,981,982,983,985,986,987,988,989,990,991,993,995,997,998,1000,1001,1002,1003,1004,1005,1006,1007,1008,1009,1011],[211,211,211,430,213,211,213,213,211],[211,211,215,443,213,211,213,213,211],[211,211,222,351,213,211,213,213,211],[211,211,248,469,213,211,213,213,211],[211,211,261,481,213,211,213,213,211],[211,211,274,435,213,211,213,213,211],[211,211,287,300,213,211,213,213,211],[211,211,299,516,213,211,213,213,211],[211,211,311,530,213,211,213,213,211],[211,211,323,541,213,211,213,213,211],[211,211,335,262,213,211,213,213,211],[211,211,346,878,213,211,213,213,211],0.839,[211,215,346,106,211,211,213,213,215],[215,211,211,220,213,211,213,213,211],[215,211,215,882,213,211,213,213,211],2.75,[215,211,222,884,213,211,213,213,211],4.91,[215,211,248,281,213,211,213,213,211],[215,211,261,357,213,211,213,213,211],[215,211,274,516,213,211,213,213,211],[215,211,287,763,213,211,213,213,211],[215,211,299,445,213,211,213,213,211],[215,211,311,264,213,211,213,213,211],[215,211,323,285,213,211,213,213,211],[215,211,335,893,213,211,213,213,211],1.58,[215,211,346,895,213,211,213,213,211],1.525,[215,215,346,897,213,211,213,213,215],0.928,[222,211,211,266,213,211,213,213,211],[222,211,215,239,213,211,213,213,211],[222,211,222,526,213,211,213,213,211],[222,211,248,266,213,211,213,213,211],[222,211,261,492,213,211,213,213,211],[222,211,274,428,213,211,213,213,211],[222,211,287,492,213,211,213,213,211],[222,211,299,492,213,211,213,213,211],[222,211,311,215,213,211,213,213,211],[222,211,323,428,213,211,213,213,211],[222,211,335,266,213,211,213,213,211],[222,211,346,910,213,211,213,213,211],0.736,[222,215,346,912,213,211,213,213,215],0.318,[248,211,211,426,213,211,213,213,211],[248,211,215,439,213,211,213,213,211],[248,211,222,215,213,211,213,213,211],[248,211,248,464,213,211,213,213,211],[248,211,261,453,213,211,213,213,211],[248,211,274,492,213,211,213,213,211],[248,211,287,324,213,211,213,213,211],[248,211,299,510,213,211,213,213,211],[248,211,311,526,213,211,213,213,211],[248,211,323,327,213,211,213,213,211],[248,211,335,551,213,211,213,213,211],[248,211,346,925,213,211,213,213,211],0.701,[248,215,346,927,213,211,213,213,215],0.294,[261,211,211,266,213,211,213,213,211],[261,211,215,930,213,211,213,213,211],2.1,[261,211,222,329,213,211,213,213,211],[261,211,248,216,213,211,213,213,211],[261,211,261,333,213,211,213,213,211],[261,211,274,462,213,211,213,213,211],[261,211,287,936,213,211,213,213,211],0.59,[261,211,299,331,213,211,213,213,211],[261,211,311,292,213,211,213,213,211],[261,211,323,678,213,211,213,213,211],[261,211,335,528,213,211,213,213,211],[261,211,346,942,213,211,213,213,211],0.883,[261,215,346,944,213,211,213,213,215],0.375,[274,211,211,317,213,211,213,213,211],[274,211,215,947,213,211,213,213,211],3.38,[274,211,222,949,213,211,213,213,211],1.86,[274,211,248,439,213,211,213,213,211],[274,211,261,241,213,211,213,213,211],[274,211,274,447,213,211,213,213,211],[274,211,287,954,213,211,213,213,211],0.88,[274,211,299,544,213,211,213,213,211],[274,211,311,957,213,211,213,213,211],1.44,[274,211,323,302,213,211,213,213,211],[274,211,335,237,213,211,213,213,211],[274,211,346,961,213,211,213,213,211],1.551,[274,215,346,963,213,211,213,213,215],0.737,[287,211,211,541,213,211,213,213,211],[287,211,215,682,213,211,213,213,211],[287,211,222,541,213,211,213,213,211],[287,211,248,426,213,211,213,213,211],[287,211,261,428,213,211,213,213,211],[287,211,274,676,213,211,213,213,211],[287,211,287,456,213,211,213,213,211],[287,211,299,555,213,211,213,213,211],[287,211,311,973,213,211,213,213,211],0.87,[287,211,323,435,213,211,213,213,211],[287,211,335,300,213,211,213,213,211],[287,211,346,977,213,211,213,213,211],0.676,[287,215,346,979,213,211,213,213,215],0.291,[299,211,211,216,213,211,213,213,211],[299,211,215,239,213,211,213,213,211],[299,211,222,315,213,211,213,213,211],[299,211,248,984,213,211,213,213,211],0.81,[299,211,261,464,213,211,213,213,211],[299,211,274,684,213,211,213,213,211],[299,211,287,426,213,211,213,213,211],[299,211,299,324,213,211,213,213,211],[299,211,311,469,213,211,213,213,211],[299,211,323,460,213,211,213,213,211],[299,211,335,992,213,211,213,213,211],1.02,[299,211,346,994,213,211,213,213,211],0.857,[299,215,346,996,213,211,213,213,215],0.363,[311,211,211,266,213,211,213,213,211],[311,211,215,999,213,211,213,213,211],1.33,[311,211,222,469,213,211,213,213,211],[311,211,248,936,213,211,213,213,211],[311,211,261,678,213,211,213,213,211],[311,211,274,771,213,211,213,213,211],[311,211,287,453,213,211,213,213,211],[311,211,299,485,213,211,213,213,211],[311,211,311,268,213,211,213,213,211],[311,211,323,541,213,211,213,213,211],[311,211,335,288,213,211,213,213,211],[311,211,346,1010,213,211,213,213,211],0.756,[311,215,346,1012,213,211,213,213,215],0.366,[1014],"not_reported (dash in table)",[373],[],[],[1019,1020],"KITTI odometry 00-10, relative translation error; baseline values imported from their published papers (not rerun); SLAMesh without loop closure; w\u002Fo Comb. and w\u002Fo P2Mesh are ablations","KITTI odometry 00-10, relative translation error; baseline values imported from their published papers (not rerun); SLAMesh without loop closure; w\u002Fo Comb. and w\u002Fo P2Mesh are ablations; only the Mean column of the rotation row is extracted",[1022,1027,1032,1038,1043,1048,1054,1060,1065,1072,1078],{"group":1023,"slug":1024,"sourceLabel":1025,"table":373,"selfRows":520,"datasets":1026},"saloam2021:Table II","saloam2021-table-ii","Li et al., 2021a",[592],{"group":1028,"slug":1029,"sourceLabel":1025,"table":1030,"selfRows":311,"datasets":1031},"saloam2021:Table III","saloam2021-table-iii","Table III",[592],{"group":1033,"slug":1034,"sourceLabel":1025,"table":1035,"selfRows":248,"datasets":1036},"saloam2021:Table IV","saloam2021-table-iv","Table IV",[1037],"Ford Campus Vision and Lidar Dataset",{"group":1039,"slug":1040,"sourceLabel":6,"table":1041,"selfRows":248,"datasets":1042},"sumapp2019:Text Sec.IV","sumapp2019-text-sec-iv","Text Sec.IV",[94,380],{"group":1044,"slug":1045,"sourceLabel":1046,"table":373,"selfRows":222,"datasets":1047},"kissicp2023:Table II","kissicp2023-table-ii","Vizzo et al., 2023",[592],{"group":1049,"slug":1050,"sourceLabel":6,"table":1051,"selfRows":222,"datasets":1052},"sumapp2019:Text Sec.IV-B","sumapp2019-text-sec-iv-b","Text Sec.IV-B",[1053],"KITTI odometry (test)",{"group":1055,"slug":1056,"sourceLabel":1057,"table":159,"selfRows":222,"datasets":1058},"zhu2025meshloam:Table I","zhu2025meshloam-table-i","Zhu et al., 2025",[1059],"KITTI Odometry",{"group":1061,"slug":1062,"sourceLabel":1063,"table":1030,"selfRows":215,"datasets":1064},"genzicp2025:Table III","genzicp2025-table-iii","Lee et al., 2025a",[592],{"group":1066,"slug":1067,"sourceLabel":1068,"table":1069,"selfRows":215,"datasets":1070},"ghadimzadeh2025slamnde:Table 3","ghadimzadeh2025slamnde-table-3","Ghadimzadeh Alamdari et al., 2025","Table 3",[1071],"Luleå SubT tunnel dataset (Koval et al. 2022)",{"group":1073,"slug":1074,"sourceLabel":1075,"table":1076,"selfRows":215,"datasets":1077},"zhang2024_3dlidarslam_survey:Table 8","zhang2024-3dlidarslam-survey-table-8","Zhang et al., 2024a","Table 8",[592],{"group":1079,"slug":1080,"sourceLabel":1075,"table":1081,"selfRows":215,"datasets":1082},"zhang2024_3dlidarslam_survey:Table 9","zhang2024-3dlidarslam-survey-table-9","Table 9",[592],1790510663466]