Depth completion aims to generate a dense depth map from the sparse depth map and aligned RGB image. However, current depth completion methods use extremely expensive 64-line LiDAR(about $100,000) to obtain sparse depth maps, which will limit their application scenarios. Compared with the 64-line LiDAR, the single-line LiDAR is much less expensive and much more robust. Therefore, we propose a method to tackle the problem of single-line depth completion, in which we aim to generate a dense depth map from the single-line LiDAR info and the aligned RGB image. A single-line depth completion dataset is proposed based on the existing 64-line depth completion dataset(KITTI). A network called Semantic Guided Two-Branch Network(SGTBN) which contains global and local branches to extract and fuse global and local info is proposed for this task. A Semantic guided depth upsampling module is used in our network to make full use of the semantic info in RGB images. Except for the usual MSE loss, we add the virtual normal loss to increase the constraint of high-order 3D geometry in our network. Our network outperforms the state-of-the-art in the single-line depth completion task. Besides, compared with the monocular depth estimation, our method also has significant advantages in precision and model size.

翻译：深度完成的目的是从稀薄的深度地图和相匹配的 RGB 图像中生成一个密密的深度地图。 然而,当前深度完成方法使用极其昂贵的64线LIDAR(约100 000美元)来获取稀薄的深度地图,这将限制其应用情景。 与64线LIDAR相比,单线LIDAR的深度完成方法的成本要低得多,而且要强得多。 因此,我们提出了一个方法来解决单线深度完成问题,我们的目标是从单线LIDAR Info 和对齐的 RGB 图像中生成一个密密的深度地图。 在现有的64线深度完成数据集(KITTI)的基础上,提出了一个单线深度完成数据集。 一个名为Semanitic 向导双层网络(SGTBN)的网络,该网络包含全球和地方分支,可以提取和连接全球和本地信息,而且更稳健。 我们的深度测试模块使用一个深度模块,以充分利用RGB 图像中的语义信息。除了通常的MSE损失外,我们增加虚拟正常的深度数据损失,以增加高端的深度网络的深度 3D 的深度的深度 。 我们的深度任务中, 的模型的模型的深度比比重的模型的深度任务的深度的深度的深度, 的深度定义的深度的模型的深度的深度分析。