KPRNet: Improving projection-based LiDAR semantic segmentation
This work addresses the perception needs of autonomous vehicles, representing an incremental improvement over existing methods.
The paper tackled the problem of LiDAR semantic segmentation for autonomous vehicles by improving projection-based methods with a novel CNN architecture and a learnable point-wise component, achieving a state-of-the-art mIoU of 63.1 on the SemanticKITTI benchmark.
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.