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
1KP-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.
2AutoNN0.7630.941838.600.9580.8870.8410.4630.9520.4550.7440.808
Anonymous submission
3NI_IMP_EU_TEST10.7270.9322400.000.9400.8940.8650.4550.9340.2730.7210.734
IMP EU SunWei
4RGNet0.7470.9451.000.9750.9300.8810.4810.9460.3620.7200.680
Fast Point Cloud Registration Using Semantic Segmentation - DICTA 2019
5RandLA-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)
6PAI_Conv0.7640.9441.000.9640.9040.8670.4960.9560.4540.6900.784
Anonymous submission
7SPGraph0.7320.9403000.000.9740.9260.8790.4400.9320.3100.6350.762
Large-scale Point cloud segmentation with superpoint graphs, Loic Landrieu and Martin Simonovsky, CVPR2018
8PAI-Conv-v20.7200.9211.000.8870.7790.8560.4660.9530.4370.6210.764
Anonymous submission
9new_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.
10MSDeepVoxNet0.6530.884115000.000.8300.6720.8380.3670.9240.3130.5000.782
Classification of Point Cloud Scenes with Multiscale Voxel Deep Network, Xavier Roynard, Jean-Emmanuel Deschaud and François Goulette
11OctFCNNet0.6480.8941200.000.9430.7560.7860.3420.9040.2570.4780.721
Anonymous submission
12shell_v20.6850.9323000.000.9730.9100.8370.3970.9310.2710.4480.715
Anonymous submission
13shellnet_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.
14GACNet0.7080.9191380.000.8640.7770.8850.6060.9420.3730.4350.778
Anonymous submission
15RF_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.
16MS-RRFSegnet0.7250.9302560.000.8950.8360.8370.4310.9600.5360.3900.917
Anonymous submission
17SnapNet_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
18TMLC-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
19PCSNet0.7120.9431500.000.9710.9500.8790.5250.9410.3880.3550.687
20RSSP0.6470.920359.000.9160.8700.8700.5250.9300.1580.3200.589
Anonymous submission
21DLUT_SR0.5630.8601.000.9530.8490.5480.2960.8320.1920.3200.518
Anonymous submission
22OctreeNet_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.
23DeepVoxNet0.5710.848100000.000.8270.5310.8380.2870.8990.2360.2980.650
Classification of Point Cloud Scenes with Multiscale Voxel Deep Network, Xavier Roynard, Jean-Emmanuel Deschaud and François Goulette
24SEGCloud0.6130.8811881.000.8390.6600.8600.4050.9110.3090.2750.643
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
253D-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
26DeePr3SS0.5850.8890.000.8560.8320.7420.3240.8970.1850.2510.592
F. Lawin, M. Danelljan, P. Tosteberg, G. Bhat, F. Khan, M. Felsberg. Deep Projective 3D Semantic Segmentation. In , 2017.
27DeepNet0.4370.77264800.000.8380.3850.5480.0850.8410.1510.2230.423
Anonymous submission
28WYJ_JTP0.0020.0061000.000.0010.0000.0010.0050.0040.0070.0000.000
Anonymous submission
29TML-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
30NLNN0.2030.5391.000.0000.0000.8640.2510.5060.0000.0000.000
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}
 }