RangeNet++: Fast and Accurate LiDAR Semantic Segmentation

IROS'2019 submission - Andres Milioto, Ignacio Vizzo, Jens Behley, Cyrill Stachniss.

Predictions from Sequence 13 Kitti dataset. Each frame is processed individually, and in under 100ms in a single GPU, under the frame rate of a Velodyne LiDAR scanner.

Code and data coming soon.

Resources:
CODE Slam [SuMa]: https://github.com/jbehley/SuMa
CODE Semantics [Lidar-Bonnetal]: https://github.com/PRBonn/lidar-bonnetal
Kitti dataset: http://www.cvlibs.net/datasets/kitti/
Semantic dataset: http://semantic-kitti.org

We thank NVIDIA Corporation for providing a Quadro P6000 GPU used to support this research.

Видео RangeNet++: Fast and Accurate LiDAR Semantic Segmentation канала Andres Milioto