论文标题
P2NET：基于连续帧的一致性，用于精炼LiDAR点云语义分割的后处理网络
P2Net: A Post-Processing Network for Refining Semantic Segmentation of LiDAR Point Cloud based on Consistency of Consecutive Frames
论文作者
论文摘要
我们提出了一种轻巧的后处理方法，以完善点云序列的语义分割结果。大多数现有的方法通常按框架进行细分，并遇到问题的固有歧义：基于单个帧中的测量，有时甚至对于人类来说，标签也很难预测。为了解决这个问题，我们建议明确培训网络，以完善通过现有分割方法预测的这些结果。我们称之为P2NET的网络了解了注册后连续帧的一致点之间的一致性约束。我们在由真实室外场景组成的Semantickitti数据集上进行定性和定量评估所提出的后处理方法。通过比较有和没有后处理网络改进的两个代表性网络预测的结果来验证所提出方法的有效性。具体而言，定性可视化验证了可以用P2NET校正难以预测的点标签的关键思想。在数量上，PointNet [1]的总体MIOU从10.5％提高到11.7％，对于PointNet ++ [2]，MIOU的总体MIOU [1]和15.9％。
We present a lightweight post-processing method to refine the semantic segmentation results of point cloud sequences. Most existing methods usually segment frame by frame and encounter the inherent ambiguity of the problem: based on a measurement in a single frame, labels are sometimes difficult to predict even for humans. To remedy this problem, we propose to explicitly train a network to refine these results predicted by an existing segmentation method. The network, which we call the P2Net, learns the consistency constraints between coincident points from consecutive frames after registration. We evaluate the proposed post-processing method both qualitatively and quantitatively on the SemanticKITTI dataset that consists of real outdoor scenes. The effectiveness of the proposed method is validated by comparing the results predicted by two representative networks with and without the refinement by the post-processing network. Specifically, qualitative visualization validates the key idea that labels of the points that are difficult to predict can be corrected with P2Net. Quantitatively, overall mIoU is improved from 10.5% to 11.7% for PointNet [1] and from 10.8% to 15.9% for PointNet++ [2].
