KPRNet: Improving projection-based LiDAR semantic segmentation

by   Deyvid Kochanov, et al.

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 [11] 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.


page 1

page 2

page 3

page 4


LEST: Large-scale LiDAR Semantic Segmentation with Transformer

Large-scale LiDAR-based point cloud semantic segmentation is a critical ...

3D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentation

LIDAR semantic segmentation, which assigns a semantic label to each 3D p...

FIDNet: LiDAR Point Cloud Semantic Segmentation with Fully Interpolation Decoding

Projecting the point cloud on the 2D spherical range image transforms th...

DeepTemporalSeg: Temporally Consistent Semantic Segmentation of 3D LiDAR Scans

Understanding the semantic characteristics of the environment is a key e...

AMVNet: Assertion-based Multi-View Fusion Network for LiDAR Semantic Segmentation

In this paper, we present an Assertion-based Multi-View Fusion network (...

A Near Sensor Edge Computing System for Point Cloud Semantic Segmentation

Point cloud semantic segmentation has attracted attentions due to its ro...

Please sign up or login with your details

Forgot password? Click here to reset