semantic-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
1SPGraph_0.7620.92910000.000.9150.7560.7830.7170.9440.5680.5290.884
Large-scale Point cloud segmentation with superpoint graphs, Loic Landrieu and Martin Simonovsky, CVPR2018
2LightConvPoint.0.7460.9411000000.000.9470.8520.7740.7040.9400.5290.2940.926
FKAConv: Feature-Kernel Alignment for Point Cloud Convolution -- https://arxiv.org/abs/2004.04462 implemented in LightConvPoint Framework
3WreathProdNet0.7710.9461.000.9520.8710.7530.6710.9610.5130.5100.934
@misc{wang2020equivariant, title={Equivariant Maps for Hierarchical Structures}, author={Renhao Wang and Marjan Albooyeh and Siamak Ravanbakhsh}, year={2020}, eprint={2006.03627}, archivePrefix={arXiv}, primaryClass={cs.LG} }
453540.7630.948100.000.9670.9270.7000.6250.9420.5080.4940.938
Anonymous submission
5ddnet0.7470.9501.000.9790.9410.7080.6430.9400.4850.3880.892
Anonymous submission
6conv_pts0.7650.9342400.000.9210.8060.7600.7190.9560.4730.6110.877
Generalizing discrete convolutions for unstructured point clouds, A. Boulch, Eurographics 3DOR, 2019
7GeomAdapt0.7520.9471.000.9630.8970.7090.6720.9600.4570.4580.903
8dp_v40.7520.9381000.000.9470.8400.7340.6290.9640.4540.5110.939
Anonymous submission
9Wow0.7200.9061.000.8640.7030.6950.6800.9690.4340.5230.895
Fast Point Cloud Registration Using Semantic Segmentation - DICTA 2019
10ConvPoint_Keras0.7770.9501.000.9590.9000.7910.7050.9630.4330.5610.907
11Att_conv0.7070.9361.000.9630.8960.6830.6070.9280.4150.2720.898
Attentive Aggregation Networks for Efficient Semantic Segmentation of Large-Scale Point Clouds
12PointConv_CE0.7100.9231.000.9240.7960.7270.6200.9370.4060.4460.825
Semantic Context Encoding for Accurate 3D Point Cloud Segmentation. IEEE Transactions on Multimedia 2020
133DNet0.7320.938400.000.9780.9240.6530.5940.9220.3960.4510.934
Anonymous submission
14PointGCR0.6950.9212.000.9380.8000.6440.6640.9320.3920.3430.853
Global Context Reasoning for Semantic Segmentation of 3D Point Clouds. Submitted to WACV 2020
15SnapNet0.6740.9100.000.8960.7950.7480.5610.9090.3650.3430.772
Unstructured point cloud semantic labeling using deep segmentation networks. A. Boulch, B. Le Saux and N. Audebert, Eurographics 3DOR 2017
16PointNet2_Demo0.6310.85710000.000.8190.7810.6430.5170.7590.3640.4370.726
https://github.com/IntelVCL/Open3D-PointNet2-Semantic3D, Yixing Lao
17pointnetpp_sem0.5210.82510000.000.7880.7450.5980.6080.8170.3320.1540.127
G. Dekeyser and M. Orhan
18super_ss0.6440.8961.000.9110.6950.6500.5600.8970.3000.4380.697
@inproceedings{contreras2019edge, title={Edge-Convolution Point Net for Semantic Segmentation of Large-Scale Point Clouds}, author={Contreras, Jhonatan and Denzler, Joachim}, booktitle={IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium}, pages={5236--5239}, year={2019}, organization={IEEE} }
19ILiDAR-C1DC0.6200.914604800.000.9180.7980.5760.6720.9380.2940.2090.557
Anonymous submission
20HarrisNet0.6230.8810.000.8180.7370.7420.6250.9270.2830.1780.671
Anonymous submission
21FCNVoxNet0.3720.523138929.000.0660.2720.5800.3640.8090.2830.0950.509
Anonymous submission
22TMLC-MS0.4940.85038421.000.9110.6950.3280.2160.8760.2590.1130.553
Timo Hackel, Jan D. Wegner, Konrad Schindler: Fast semantic segmentation of 3d point clouds with strongly varying density. ISPRS Annals - ISPRS Congress, Prague, 2016
23TML-PC0.3910.7450.000.8040.6610.4230.4120.6470.1240.0000.058
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

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}
 }