论文标题
LMSCNET：轻巧的多尺度3D语义完成
LMSCNet: Lightweight Multiscale 3D Semantic Completion
论文作者
论文摘要
我们从Voxelized稀疏3D激光扫描中介绍了一种新的多尺度3Smantic场景完成方法。与文献相比，我们使用具有全面的多尺度跳过连接的2D UNET主链，以增强特征流以及3D分割头。在Semantickitti基准测试中，我们的方法在语义完成方面执行了标准杆，并且比所有其他已发表的方法都更好，同时更加轻松，更快。因此，它为移动机器人应用程序提供了出色的性能/速度权衡。消融研究表明，我们的方法对较低的密度输入具有鲁棒性，并且可以使最高级别的语义完成在最高的水平上。我们的代码可在https://github.com/cv-rits/lmscnet上找到。
We introduce a new approach for multiscale 3Dsemantic scene completion from voxelized sparse 3D LiDAR scans. As opposed to the literature, we use a 2D UNet backbone with comprehensive multiscale skip connections to enhance feature flow, along with 3D segmentation heads. On the SemanticKITTI benchmark, our method performs on par on semantic completion and better on occupancy completion than all other published methods -- while being significantly lighter and faster. As such it provides a great performance/speed trade-off for mobile-robotics applications. The ablation studies demonstrate our method is robust to lower density inputs, and that it enables very high speed semantic completion at the coarsest level. Our code is available at https://github.com/cv-rits/LMSCNet.
