arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.10544cs.CV
收藏

TORNADO-Net:mulTiview tOtal vaRiatioN使用Diamond inceptiOn模块的语义分割

TORNADO-Net: mulTiview tOtal vaRiatioN semAntic segmentation with Diamond inceptiOn module

Martin Gerdzhev, Ryan Razani, Ehsan Taghavi, Bingbing Liu

摘要:

点云的语义分割是机器人和自动驾驶场景理解的关键组成部分。在本文中,我们介绍了TORNADO网络-一个神经网络的三维激光雷达点云语义分割。我们将多视图(鸟瞰和范围)投影特征提取与具有新颖的菱形上下文块的编码器-解码器ResNet架构相结合。目前基于投影的方法没有考虑到相邻点通常属于同一类。为了更好地利用这种局部邻域信息并减少噪声预测,我们引入了总变差,Lovasz-Softmax和加权交叉熵损失的组合。我们还利用了LiDAR数据涵盖360度视场并使用圆形填充的事实。我们在SemanticKITTI数据集上展示了最先进的结果,并提供了全面的定量评估和消融结果。

英文摘要:

Semantic segmentation of point clouds is a key component of scene understanding for robotics and autonomous driving. In this paper, we introduce TORNADO-Net - a neural network for 3D LiDAR point cloud semantic segmentation. We incorporate a multi-view (bird-eye and range) projection feature extraction with an encoder-decoder ResNet architecture with a novel diamond context block. Current projection-based methods do not take into account that neighboring points usually belong to the same class. To better utilize this local neighbourhood information and reduce noisy predictions, we introduce a combination of Total Variation, Lovasz-Softmax, and Weighted Cross-Entropy losses. We also take advantage of the fact that the LiDAR data encompasses 360 degrees field of view and uses circular padding. We demonstrate state-of-the-art results on the SemanticKITTI dataset and also provide thorough quantitative evaluations and ablation results.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑