KPRNet: Improving projection-based LiDAR semantic segmentation

24 Jul 2020  ·  Deyvid Kochanov, Fatemeh Karimi Nejadasl, Olaf Booij ·

Semantic segmentation is an important component in the perception systems of autonomous vehicles. In this work, we adopt recent advances in both image and point cloud segmentation to achieve a better accuracy in the task of segmenting LiDAR scans. KPRNet improves the convolutional neural network architecture of 2D projection methods and utilizes KPConv to replace the commonly used post-processing techniques with a learnable point-wise component which allows us to obtain more accurate 3D labels. With these improvements our model outperforms the current best method on the SemanticKITTI benchmark, reaching an mIoU of 63.1.

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Semantic Segmentation SemanticKITTI KPRNet test mIoU 63.1% # 15

Methods


No methods listed for this paper. Add relevant methods here