reduced-8 results

We use Intersection over Union (IoU) and Overall Accuracy (OA) as metrics. For more details hover the curser over the symbols or click on a classifier. In order to sort the results differently click on a symbol.

NameA_IoUOA[s]IoU 1IoU 2IoU 3IoU 4IoU 5IoU 6IoU 7IoU 8
1CASIA_VSLab0.7200.902243.060.7930.8290.9130.5360.8880.4540.6330.718
Anonymous submission
2EU_IMP0.7960.9551.000.9760.9440.9120.6280.9600.5040.6760.767
Anonymous submission
3SPNet0.7700.9451300.000.9750.9000.8920.5110.9510.4210.7270.786
Anonymous submission
4AI_Lab-NIE0.7920.9551.000.9720.9420.8900.5720.9640.5030.7130.777
Anonymous submission
5GACNet0.7080.9191380.000.8640.7770.8850.6060.9420.3730.4350.778
Anonymous submission
6RGNet0.7470.9451.000.9750.9300.8810.4810.9460.3620.7200.680
Fast Point Cloud Registration Using Semantic Segmentation - DICTA 2019
7XPCONVP0.7780.946111.000.9710.9110.8790.5320.9480.4150.7570.811
Anonymous submission
8SPGraph0.7320.9403000.000.9740.9260.8790.4400.9320.3100.6350.762
Large-scale Point cloud segmentation with superpoint graphs, Loic Landrieu and Martin Simonovsky, CVPR2018
9IGDC0.7830.9512.000.9770.9400.8790.5260.9530.4670.7220.799
Anonymous submission
10PCSNet0.7120.9431500.000.9710.9500.8790.5250.9410.3880.3550.687
11BRNet_0910_20.7770.9501.000.9730.9410.8770.5220.9550.4820.6770.790
Anonymous submission
12PG_Net0.7720.9440.000.9470.8880.8750.5340.9530.5280.6550.793
Kangcheng Liu, and Ben M. Chen. (FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling) https://arxiv.org/abs/2012.09439
13RSSP0.6470.920359.000.9160.8700.8700.5250.9300.1580.3200.589
Anonymous submission
14TBDV20.8000.9541.000.9710.9350.8680.5510.9590.5310.7530.829
Anonymous submission
15PAI_Conv0.7640.9441.000.9640.9040.8670.4960.9560.4540.6900.784
Anonymous submission
16ds0.7740.94823.000.9560.9140.8660.5150.9570.5150.6980.768
Anonymous submission
17RandLA-Net0.7740.9481.000.9560.9140.8660.5150.9570.5150.6980.768
RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds (CVPR 2020, Oral)
18FilterNet0.7310.930100.000.8980.8320.8650.5150.9510.3850.6280.778
Anonymous submission
19NLNN0.2030.5391.000.0000.0000.8640.2510.5060.0000.0000.000
Anonymous submission
20SCF-Net0.7760.947563.600.9710.9180.8630.5120.9530.5050.6790.807
SCF-Net: Learning Spatial Contextual Features for Large-Scale Point Cloud Segmentation (CVPR2021)
21SEGCloud0.6130.8811881.000.8390.6600.8600.4050.9110.3090.2750.643
L. P. Tchapmi, C. B.Choy, I. Armeni, J. Gwak, S. Savarese, SEGCloud: Semantic Segmentation of 3D Point Clouds, International Conference on 3D Vision (3DV), 2017
22RFCR0.7780.9431.000.9420.8910.8570.5440.9500.4380.7620.837
Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning (CVPR2021)
23AnchorConv_AR0.7770.949111.000.9760.9300.8570.5310.9510.4210.7210.827
Anonymous submission
24PAI-Conv-v20.7200.9211.000.8870.7790.8560.4660.9530.4370.6210.764
Anonymous submission
25CRFConv0.7230.9410.100.9770.9230.8480.4660.9500.4000.4050.812
Anonymous submission
26UDNV0.7730.945259200.000.9570.9030.8440.5050.9540.4590.7270.832
Anonymous submission
27PyramidPoint0.7730.9451.000.9570.9030.8440.5050.9540.4590.7270.832
https://arxiv.org/abs/2011.08692
28KP-FCNN0.7460.929600.000.9090.8220.8420.4790.9490.4000.7730.797
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas. KPConv: Flexible and Deformable Convolution for Point Clouds. In The IEEE International Conference on Computer Vision (ICCV), 2019.
29AutoNN0.7630.941838.600.9580.8870.8410.4630.9520.4550.7440.808
Anonymous submission
3010GRU0.6730.91110800.000.9750.7690.8400.3190.9350.2620.5870.700
Anonymous submission
31shellnet_v20.6930.9323000.000.9630.9040.8390.4100.9420.3470.4390.702
Z. Zhang, S. Hua, K. Yeung. ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statistics. In International Conference on Computer Vision (ICCV), 2019.
32AGMMConv0.7610.9500.100.9770.9390.8390.5000.9580.4980.5290.848
Anonymous submission
33MSDeepVoxNet0.6530.884115000.000.8300.6720.8380.3670.9240.3130.5000.782
Classification of Point Cloud Scenes with Multiscale Voxel Deep Network, Xavier Roynard, Jean-Emmanuel Deschaud and François Goulette
34DeepVoxNet0.5710.848100000.000.8270.5310.8380.2870.8990.2360.2980.650
Classification of Point Cloud Scenes with Multiscale Voxel Deep Network, Xavier Roynard, Jean-Emmanuel Deschaud and François Goulette
35shell_v20.6850.9323000.000.9730.9100.8370.3970.9310.2710.4480.715
Anonymous submission
36MS-RRFSegnet0.7250.9302560.000.8950.8360.8370.4310.9600.5360.3900.917
Anonymous submission
37OctreeNet_CRF0.5910.899184.840.9070.8200.8240.3930.9000.1090.3120.460
F. Wang, Y. Zhuang, H. Gu, and H. Hu, OctreeNet:A Novel Sparse 3D Convolutional Neural Network for Real-time 3D Outdoor Scene Analysis, submitted to IEEE Transactions on Automation Science and Engineering.
38CRFConv_big0.7490.9420.100.9810.9110.8180.4480.9520.4080.5940.880
Anonymous submission
39DG0.6820.91223.840.9650.8690.8180.3820.9160.2870.5580.658
Anonymous submission
40RF_MSSF0.6270.9031643.750.8760.8030.8180.3640.9220.2410.4260.566
H. Thomas, J. Deschaud, B. Marcotegui, F. Goulette, Y. Le Gall. Semantic Classification of 3D Point Clouds with Multiscale Spherical Neighborhoods. In 3D Vision (3DV), 2018 International Conference on, 2018.
41LU-10.7060.91518.450.9520.8890.8150.3620.9130.3340.6020.779
surveying and mapping institute
42ACNNs0.6130.9081.000.9400.8620.8040.1850.9040.2450.2900.673
Anonymous submission
43SnapNet_0.5910.8863600.000.8200.7730.7970.2290.9110.1840.3730.644
Unstructured point cloud semantic labeling using deep segmentation networks. A. Boulch, B. Le Saux and N. Audebert, Eurographics 3DOR 2017
44OctFCNNet0.6480.8941200.000.9430.7560.7860.3420.9040.2570.4780.721
Anonymous submission
45NI_IMP_EU_TEST10.5560.8592400.000.8570.8280.7780.3600.8870.2280.4160.093
IMP EU SunWei
463D-FCNN-TI0.5820.875774.000.8400.7110.7700.3180.8990.2770.2520.590
L. P. Tchapmi, C. B.Choy, I. Armeni, J. Gwak, S. Savarese, SEGCloud: Semantic Segmentation of 3D Point Clouds, International Conference on 3D Vision (3DV), 2017
47new_net0.5950.879100000.000.8450.7090.7660.2610.9140.1860.5650.514
J. Contreras, J. Denzler. Edge-Convolution Point Net for Semantic Segmentation of Large-Scale Point Clouds. In IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium, 2019.
48XJTLU0.6350.894367.000.8540.7440.7460.3190.9300.2520.4150.820
Cai Y, Huang H, Wang K, Zhang C, Fan L, Guo F. Selecting Optimal Combination of Data Channels for Semantic Segmentation in City Information Modelling (CIM). Remote Sensing. 2021; 13(7):1367. https://doi.org/10.3390/rs13071367
49DeePr3SS0.5850.8890.000.8560.8320.7420.3240.8970.1850.2510.592
F. Lawin, M. Danelljan, P. Tosteberg, G. Bhat, F. Khan, M. Felsberg. Deep Projective 3D Semantic Segmentation. In , 2017.
5010GRUDeep30.4680.79010800.000.4750.4810.6920.2680.9200.1800.3090.422
Anonymous submission
51ThickSeg3D0.5250.864228.010.8370.7380.5530.2600.9050.1410.2560.510
Anonymous submission
52DLUT_SR0.5630.8601.000.9530.8490.5480.2960.8320.1920.3200.518
Anonymous submission
53DeepNet0.4370.77264800.000.8380.3850.5480.0850.8410.1510.2230.423
Anonymous submission
54TMLC-MSR0.5420.8621800.000.8980.7450.5370.2680.8880.1890.3640.447
Timo Hackel, Jan D. Wegner, Konrad Schindler: Fast semantic segmentation of 3d point clouds with strongly varying density. ISPRS Annals - ISPRS Congress, Prague, 2016
55TML-PCR0.3840.7400.000.7260.7300.4850.2240.7070.0500.0000.150
Mind the gap: modeling local and global context in (road) networks: Javier Montoya, Jan D. Wegner, Lubor Ladicky, Konrad Schindler. In: German Conference on Pattern Recognition (GCPR), Münster, Germany, 2014
56WYJ_JTP0.0020.0061000.000.0010.0000.0010.0050.0040.0070.0000.000
Anonymous submission

References


  @inproceedings{hackel2017isprs,
   title={{SEMANTIC3D.NET: A new large-scale point cloud classification benchmark}},
   author={Timo Hackel and N. Savinov and L. Ladicky and Jan D. Wegner and K. Schindler and M. Pollefeys},
   booktitle={ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences},
   year = {2017},
   volume = {IV-1-W1},
   pages = {91--98}
 }