A neural network learns obstacle shapes as Signed Distance Functions from LiDAR, but only training-loss results are reported and the collision-safety claim is not tested.
Map-Based Precision Vehicle Localization in Urban Environments,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Implicit 3D scene reconstruction using deep learning towards efficient collision understanding in autonomous driving
A neural network learns obstacle shapes as Signed Distance Functions from LiDAR, but only training-loss results are reported and the collision-safety claim is not tested.