[{"data":1,"prerenderedAt":389},["ShallowReactive",2],{"method-genzicp2025":3},{"method":4,"reference":56,"equipment":78,"figures":79,"results":80},{"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":32,"platform":34,"estimator":38,"association":39,"timeModel":40,"deskew":41,"loopClosure":42,"globalOptimization":42,"mapRepresentation":43,"prior":42,"outputGeometry":44,"compute":45,"codeUrl":46,"codeLicense":47,"relatedVersions":48},"genzicp2025","Lee et al., 2025a","GenZ-ICP","GenZ-ICP: Generalizable and Degeneracy-Robust LiDAR Odometry Using an Adaptive Weighting",2025,"recent","C05","odometry_with_local_mapping","GenZ-ICP 指出單一誤差度量在不同幾何環境各有弱點：點到平面在長廊等退化場景易病態，點到點在結構化場景精度較低。作者依鄰域平面度把點分為平面與非平面兩類，分別套用點到平面與點到點誤差，並以兩類點數比例自適應調整權重，以避免最佳化在走廊型退化中發散。","Combines point-to-plane and point-to-point residuals in ICP with an adaptive weight driven by the proportion of planar points, to stay well-conditioned in corridor-like degeneracy.","full_text_reviewed","peer_reviewed_published","supplementary","not_reported（長廊退化場景與施工中建物走廊相似，但論文未於工地驗證；推論）",[20],"public_benchmark",[22,23,24,25],"Resilience to optimization degradation in corridor sequences (HILTI-Oxford Exp07, Ground-Challenge, SubT-MRS) (abstract; Sec. IV)","SubT-MRS Long_Corridor APE RMSE 1.99 m versus 8.72 m for KISS-ICP, 9.09 m for DLO and 45.66 m for CT-ICP (Table VI)","Highest HILTI-Oxford Exp07 score (33.33 versus 23.33 for the reimplemented Zhang et al.) (Table IV)","Lowest condition number of the translational Hessian in all three corridor sequences (Sec. IV-D; Fig. 5)",[27,28,29,30,31],"Focus restricted to one-directional corridor-like degeneracy (Sec. I)","Parameters of GenZ-ICP were tuned per dataset, and baselines without published results were tuned by the authors (Sec. IV-A)","Degeneracy baselines (Zhang et al., X-ICP) were reimplemented on a LiDAR-only framework with a constant-velocity prior rather than run with their original IMU or leg-odometry inputs (Sec. IV-A; Sec. IV-C)","In general environments KISS-ICP stays slightly better on KITTI (0.50% vs 0.51%) and on MulRan DCC and Riverside (Tables II-III)","Authors plan a LiDAR-inertial extension for aggressive motion (Sec. V)",[33],"3D LiDAR only",[35,36,37],"handheld (Newer College; HILTI-Oxford 2022)","vehicle (MulRan, KITTI)","platforms of Ground-Challenge and SubT-MRS sequences not stated in the paper","ICP minimizing a weighted sum of point-to-plane and point-to-point residuals with an adaptive weight","per-point planarity classification: point-to-plane for planar neighbourhoods, point-to-point otherwise","discrete poses","not_reported (motion compensation is not described in the paper)","none","local map used as ICP target (Fig. 2); its data structure is not described in the paper; metric comparison on Long_Corridor run inside the KISS-ICP framework [5] (Sec. IV-A)","odometry and accumulated map (Fig. 1); export format not_reported","not_reported (the paper states no runtime, processing rate or computing hardware)","https:\u002F\u002Fgithub.com\u002Fcocel-postech\u002Fgenz-icp","MIT (LICENSE file checked; copyright notice names KISS-ICP authors, suggesting derived code (inference))",[49,53],{"relation":50,"title":51,"doi_or_url":52},"preprint","GenZ-ICP (arXiv v1)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.06766",{"relation":54,"title":55,"doi_or_url":46},"code_release","cocel-postech\u002Fgenz-icp",{"id":5,"kind":57,"shortName":7,"title":8,"authors":58,"year":9,"venue":62,"venueType":63,"publisher":64,"volumeIssuePages":65,"doi":66,"arxivId":67,"url":68,"firstPublicDate":69,"publicationStatus":16,"metadataStatus":70,"fulltextStatus":15,"era":10,"classicReason":71,"codeUrl":46,"cluster":11,"topics":72,"mdpi":74,"verification":75,"label":6,"fulltextRoute":76,"versionRead":77,"addedByCensus":74},"method",[59,60,61],"Daehan Lee","Hyungtae Lim","Soohee Han","IEEE Robotics and Automation Letters","journal","IEEE","10(1):152-159","10.1109\u002Flra.2024.3498779","2411.06766","https:\u002F\u002Fapi.crossref.org\u002Fworks?query.bibliographic=GenZ-ICP...","2024-11-11","metadata_verified","not_applicable",[11,73],"C13",false,"corrected","arXiv","arXiv v1 (2411.06766v1, submitted 2024-11-11; arXiv comment states accepted to RA-L); IEEE version of record not opened",[],[],{"totalRows":81,"groupCount":82,"groups":83,"others":376},14,6,[84,187,268,319],{"slug":85,"group":86,"sourceId":5,"sourceLabel":6,"table":87,"selfRows":88,"metrics":89,"seqs":95,"entrants":106,"cells":125,"outcomes":180,"locators":182,"hardware":183,"wordings":184,"notes":185},"genzicp2025-table-ii","genzicp2025:Table II","Table II",4,[90],{"label":91,"unit":92,"statistic":93,"alignment":94},"relative translational error [%]","%","mean","not_reported",[96,100,102,104],{"dataset":97,"sequence":98,"environment":99},"MulRan","KAIST","urban driving",{"dataset":97,"sequence":101,"environment":99},"DCC",{"dataset":97,"sequence":103,"environment":99},"Riverside",{"dataset":97,"sequence":105,"environment":99},"Sejong",[107,111,114,117,120,123],{"name":108,"methodId":109,"linkable":110,"proposed":74,"self":74},"SuMa [37]","suma2018",true,{"name":112,"methodId":113,"linkable":110,"proposed":74,"self":74},"MULLS [35]","mulls2021",{"name":115,"methodId":116,"linkable":110,"proposed":74,"self":74},"F-LOAM [36]","floam2021",{"name":118,"methodId":119,"linkable":110,"proposed":74,"self":74},"KISS-ICP [5]","kissicp2023",{"name":121,"methodId":122,"linkable":110,"proposed":74,"self":74},"MAD-ICP [8]","madicp2024",{"name":124,"methodId":5,"linkable":110,"proposed":110,"self":110},"Ours (GenZ-ICP)",[126,130,133,136,139,141,143,145,147,149,151,153,155,157,159,161,163,165,167,169,171,174,176,178],[127,127,127,128,129,127,129,129,127],0,5.59,-1,[127,127,131,132,129,127,129,129,127],1,5.2,[127,127,134,135,129,127,129,129,127],2,13.86,[127,127,137,138,127,127,129,129,127],3,null,[131,127,127,140,129,127,129,129,127],2.94,[131,127,131,142,129,127,129,129,127],2.96,[131,127,134,144,129,127,129,129,127],5.42,[131,127,137,146,129,127,129,129,127],5.93,[134,127,127,148,129,127,129,129,127],3.43,[134,127,131,150,129,127,129,129,127],3.83,[134,127,134,152,129,127,129,129,127],5.47,[134,127,137,154,129,127,129,129,127],7.87,[137,127,127,156,129,127,129,129,127],2.28,[137,127,131,158,129,127,129,129,127],2.34,[137,127,134,160,129,127,129,129,127],2.89,[137,127,137,162,129,127,129,129,127],4.69,[88,127,127,164,129,127,129,129,127],2.47,[88,127,131,166,129,127,129,129,127],2.42,[88,127,134,168,129,127,129,129,127],3.24,[88,127,137,170,129,127,129,129,127],5.69,[172,127,127,173,129,127,129,129,127],5,2.27,[172,127,131,175,129,127,129,129,127],2.39,[172,127,134,177,129,127,129,129,127],3.01,[172,127,137,179,129,127,129,129,127],4.62,[181],"diverged (Div.)",[87],[],[],[186],"MulRan urban driving; relative translational error in % (KITTI metric)",{"slug":188,"group":189,"sourceId":5,"sourceLabel":6,"table":190,"selfRows":88,"metrics":191,"seqs":198,"entrants":205,"cells":220,"outcomes":262,"locators":263,"hardware":264,"wordings":265,"notes":266},"genzicp2025-table-v","genzicp2025:Table V","Table V",[192,196],{"label":193,"unit":194,"statistic":195,"alignment":94},"absolute pose error, translation, RMSE [m]","m","RMSE",{"label":197,"unit":194,"statistic":195,"alignment":94},"relative pose error, translation, RMSE [m]",[199,203],{"dataset":200,"sequence":201,"environment":202},"Ground-Challenge","Corridor1 (zigzag)","indoor corridor (degenerate)",{"dataset":200,"sequence":204,"environment":202},"Corridor2 (straight forward)",[206,207,210,213,216,219],{"name":118,"methodId":119,"linkable":110,"proposed":74,"self":74},{"name":208,"methodId":209,"linkable":110,"proposed":74,"self":74},"CT-ICP [6]","cticp2022",{"name":211,"methodId":212,"linkable":110,"proposed":74,"self":74},"DLO [14]","dlo2022",{"name":214,"methodId":215,"linkable":110,"proposed":74,"self":74},"Zhang et al. [18]","zhang2016degeneracy",{"name":217,"methodId":218,"linkable":110,"proposed":74,"self":74},"X-ICP [24]","tuna2024xicp",{"name":124,"methodId":5,"linkable":110,"proposed":110,"self":110},[221,223,225,227,229,231,233,235,236,238,240,242,243,245,247,249,251,253,254,255,256,258,259,261],[127,127,127,222,129,127,129,129,127],2.17,[127,131,127,224,129,127,129,129,127],0.15,[131,127,127,226,129,127,129,129,127],0.54,[131,131,127,228,129,127,129,129,127],0.06,[134,127,127,230,129,127,129,129,127],0.45,[134,131,127,232,129,127,129,129,127],0.08,[137,127,127,234,129,127,129,129,127],0.28,[137,131,127,228,129,127,129,129,127],[88,127,127,237,129,127,129,129,127],2.05,[88,131,127,239,129,127,129,129,127],0.07,[172,127,127,241,129,127,129,129,127],0.24,[172,131,127,228,129,127,129,129,127],[127,127,131,244,129,127,129,129,127],0.68,[127,131,131,246,129,127,129,129,127],0.16,[131,127,131,248,129,127,129,129,127],1.3,[131,131,131,250,129,127,129,129,127],0.14,[134,127,131,252,129,127,129,129,127],0.93,[134,131,131,250,129,127,129,129,127],[137,127,131,234,129,127,129,129,127],[137,131,131,250,129,127,129,129,127],[88,127,131,257,129,127,129,129,127],6.92,[88,131,131,224,129,127,129,129,127],[172,127,131,260,129,127,129,129,127],0.2,[172,131,131,250,129,127,129,129,127],[],[190],[],[],[267],"Ground-Challenge corridors; translation APE and RPE via EVO; only RMSE columns kept (mean, max, std omitted); Zhang et al. and X-ICP reimplemented by the authors on the same LiDAR-only framework",{"slug":269,"group":270,"sourceId":5,"sourceLabel":6,"table":271,"selfRows":134,"metrics":272,"seqs":274,"entrants":281,"cells":290,"outcomes":313,"locators":314,"hardware":315,"wordings":316,"notes":317},"genzicp2025-table-i","genzicp2025:Table I","Table I",[273],{"label":91,"unit":92,"statistic":93,"alignment":94},[275,279],{"dataset":276,"sequence":277,"environment":278},"Newer College","short experiment","handheld campus (structured and vegetation)",{"dataset":276,"sequence":280,"environment":278},"long experiment",[282,284,286,287,288,289],{"name":283,"methodId":113,"linkable":110,"proposed":74,"self":74},"MULLS [35] (SLAM)",{"name":285,"methodId":209,"linkable":110,"proposed":74,"self":74},"CT-ICP [6] (SLAM)",{"name":115,"methodId":116,"linkable":110,"proposed":74,"self":74},{"name":118,"methodId":119,"linkable":110,"proposed":74,"self":74},{"name":121,"methodId":122,"linkable":110,"proposed":74,"self":74},{"name":124,"methodId":5,"linkable":110,"proposed":110,"self":110},[291,293,295,297,299,301,302,304,306,308,309,311],[127,127,127,292,129,127,129,129,127],0.82,[127,127,131,294,129,127,129,129,127],1.23,[131,127,127,296,129,127,129,129,127],0.48,[131,127,131,298,129,127,129,129,127],0.58,[134,127,127,300,129,127,129,129,127],2.02,[134,127,131,138,127,127,129,129,127],[137,127,127,303,129,127,129,129,127],0.51,[137,127,131,305,129,127,129,129,127],0.96,[88,127,127,307,129,127,129,129,127],0.86,[88,127,131,305,129,127,129,129,127],[172,127,127,310,129,127,129,129,127],0.46,[172,127,131,312,129,127,129,129,127],0.94,[181],[271],[],[],[318],"Newer College; relative translational error in % (KITTI metric); baseline values taken from their papers when available, otherwise tuned by the authors; GenZ-ICP tuned per dataset",{"slug":320,"group":321,"sourceId":5,"sourceLabel":6,"table":322,"selfRows":134,"metrics":323,"seqs":326,"entrants":331,"cells":343,"outcomes":370,"locators":371,"hardware":372,"wordings":373,"notes":374},"genzicp2025-table-vi","genzicp2025:Table VI","Table VI",[324,325],{"label":193,"unit":194,"statistic":195,"alignment":94},{"label":197,"unit":194,"statistic":195,"alignment":94},[327],{"dataset":328,"sequence":329,"environment":330},"SubT-MRS","Long_Corridor","long indoor corridor (degenerate)",[332,333,334,335,338,340,341,342],{"name":118,"methodId":119,"linkable":110,"proposed":74,"self":74},{"name":208,"methodId":209,"linkable":110,"proposed":74,"self":74},{"name":211,"methodId":212,"linkable":110,"proposed":74,"self":74},{"name":336,"methodId":337,"linkable":110,"proposed":74,"self":74},"Point-to-point ICP [3]","besl1992icp",{"name":339,"methodId":138,"linkable":74,"proposed":74,"self":74},"Point-to-plane ICP [4]",{"name":214,"methodId":215,"linkable":110,"proposed":74,"self":74},{"name":217,"methodId":218,"linkable":110,"proposed":74,"self":74},{"name":124,"methodId":5,"linkable":110,"proposed":110,"self":110},[344,346,347,349,350,352,354,355,356,358,359,361,363,364,365,368],[127,127,127,345,129,127,129,129,127],8.72,[127,131,127,250,129,127,129,129,127],[131,127,127,348,129,127,129,129,127],45.66,[131,131,127,244,129,127,129,129,127],[134,127,127,351,129,127,129,129,127],9.09,[134,131,127,353,129,127,129,129,127],1.32,[137,127,127,345,129,127,129,129,127],[137,131,127,250,129,127,129,129,127],[88,127,127,357,129,127,129,129,127],33.16,[88,131,127,244,129,127,129,129,127],[172,127,127,360,129,127,129,129,127],20.05,[172,131,127,362,129,127,129,129,127],0.38,[82,127,127,138,127,127,129,129,127],[82,131,127,138,127,127,129,129,127],[366,127,127,367,129,127,129,129,127],7,1.99,[366,131,127,369,129,127,129,129,127],0.09,[181],[322],[],[],[375],"SubT-MRS Long_Corridor (ICCV 2023 SLAM Challenge); translation APE and RPE via EVO; only RMSE columns kept; point-to-point and point-to-plane ICP run in the same framework as GenZ-ICP",[377,383],{"group":378,"slug":379,"sourceLabel":6,"table":380,"selfRows":131,"datasets":381},"genzicp2025:Table III","genzicp2025-table-iii","Table III",[382],"KITTI odometry",{"group":384,"slug":385,"sourceLabel":6,"table":386,"selfRows":131,"datasets":387},"genzicp2025:Table IV","genzicp2025-table-iv","Table IV",[388],"HILTI-Oxford 2022",1790510658165]