Skip to main content
Springer Nature Link
Account
Fig. 13 | Autonomous Robots

Fig. 13

From: LatticeNet: fast spatio-temporal point cloud segmentation using permutohedral lattices

Fig. 13

SemanticKITTI results. We compare the prediction from our LatticeNet with the results from TangentConv (Tatarchenko et al. 2018) and SplatNet (Su et al. 2018). We can observe that our approach can better learn small objects like tree trunks, despite their relatively small number of points. Additionally, the network also effectively makes use of contextual information in order to correctly predict the parking place due to the existence of nearby cars

Back to article page