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.
Name | A_IoU | OA | [s] | IoU 1 | IoU 2 | IoU 3 | IoU 4 | IoU 5 | IoU 6 | IoU 7 | IoU 8 | |
1 | PCSNet | 0.712 | 0.943 | 1500.00 | 0.971 | 0.950 | 0.879 | 0.525 | 0.941 | 0.388 | 0.355 | 0.687 |
2 | GACNet | 0.708 | 0.919 | 1380.00 | 0.864 | 0.777 | 0.885 | 0.606 | 0.942 | 0.373 | 0.435 | 0.778 |
Anonymous submission | ||||||||||||
3 | MSDeepVoxNet | 0.653 | 0.884 | 115000.00 | 0.830 | 0.672 | 0.838 | 0.367 | 0.924 | 0.313 | 0.500 | 0.782 |
Classification of Point Cloud Scenes with Multiscale Voxel Deep Network, Xavier Roynard, Jean-Emmanuel Deschaud and François Goulette | ||||||||||||
4 | SPGraph | 0.732 | 0.940 | 3000.00 | 0.974 | 0.926 | 0.879 | 0.440 | 0.932 | 0.310 | 0.635 | 0.762 |
Large-scale Point cloud segmentation with superpoint graphs, Loic Landrieu and Martin Simonovsky, CVPR2018 | ||||||||||||
5 | SEGCloud | 0.613 | 0.881 | 1881.00 | 0.839 | 0.660 | 0.860 | 0.405 | 0.911 | 0.309 | 0.275 | 0.643 |
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 | ||||||||||||
6 | 3D-FCNN-TI | 0.582 | 0.875 | 774.00 | 0.840 | 0.711 | 0.770 | 0.318 | 0.899 | 0.277 | 0.252 | 0.590 |
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 | ||||||||||||
7 | KP-FCNN | 0.715 | 0.920 | 600.00 | 0.929 | 0.778 | 0.899 | 0.430 | 0.939 | 0.273 | 0.647 | 0.823 |
Anonymous submission | ||||||||||||
8 | OctFCNNet | 0.648 | 0.894 | 1200.00 | 0.943 | 0.756 | 0.786 | 0.342 | 0.904 | 0.257 | 0.478 | 0.721 |
Anonymous submission | ||||||||||||
9 | RF_MSSF | 0.627 | 0.903 | 1643.75 | 0.876 | 0.803 | 0.818 | 0.364 | 0.922 | 0.241 | 0.426 | 0.566 |
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. | ||||||||||||
10 | DeepVoxNet | 0.571 | 0.848 | 100000.00 | 0.827 | 0.531 | 0.838 | 0.287 | 0.899 | 0.236 | 0.298 | 0.650 |
Classification of Point Cloud Scenes with Multiscale Voxel Deep Network, Xavier Roynard, Jean-Emmanuel Deschaud and François Goulette | ||||||||||||
11 | DLUT_SR | 0.563 | 0.860 | 1.00 | 0.953 | 0.849 | 0.548 | 0.296 | 0.832 | 0.192 | 0.320 | 0.518 |
Anonymous submission | ||||||||||||
12 | TMLC-MSR | 0.542 | 0.862 | 1800.00 | 0.898 | 0.745 | 0.537 | 0.268 | 0.888 | 0.189 | 0.364 | 0.447 |
Timo Hackel, Jan D. Wegner, Konrad Schindler: Fast semantic segmentation of 3d point clouds with strongly varying density. ISPRS Annals - ISPRS Congress, Prague, 2016 | ||||||||||||
13 | DeePr3SS | 0.585 | 0.889 | 0.00 | 0.856 | 0.832 | 0.742 | 0.324 | 0.897 | 0.185 | 0.251 | 0.592 |
F. Lawin, M. Danelljan, P. Tosteberg, G. Bhat, F. Khan, M. Felsberg. Deep Projective 3D Semantic Segmentation. In , 2017. | ||||||||||||
14 | SnapNet_ | 0.591 | 0.886 | 3600.00 | 0.820 | 0.773 | 0.797 | 0.229 | 0.911 | 0.184 | 0.373 | 0.644 |
Unstructured point cloud semantic labeling using deep segmentation networks. A. Boulch, B. Le Saux and N. Audebert, Eurographics 3DOR 2017 | ||||||||||||
15 | RSSP | 0.647 | 0.920 | 1.00 | 0.916 | 0.870 | 0.870 | 0.525 | 0.930 | 0.158 | 0.320 | 0.589 |
Anonymous submission | ||||||||||||
16 | DeepNet | 0.437 | 0.772 | 64800.00 | 0.838 | 0.385 | 0.548 | 0.085 | 0.841 | 0.151 | 0.223 | 0.423 |
Anonymous submission | ||||||||||||
17 | OctreeNet_CRF | 0.591 | 0.899 | 184.84 | 0.907 | 0.820 | 0.824 | 0.393 | 0.900 | 0.109 | 0.312 | 0.460 |
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. | ||||||||||||
18 | TML-PCR | 0.384 | 0.740 | 0.00 | 0.726 | 0.730 | 0.485 | 0.224 | 0.707 | 0.050 | 0.000 | 0.150 |
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 |
@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}
}