论文标题
分割引导的域适应性以有效的深度完成
Segmentation-guided Domain Adaptation for Efficient Depth Completion
论文作者
论文摘要
完整的深度信息和有效的估计器已成为自动驾驶任务的场景理解中的重要成分。基于激光雷达的深度完成的一个主要问题是，由于不相关的激光雷达点云的稀疏性质所提供的缺乏连贯的信息，因此对卷积的利用效率低下，这通常会导致复杂和资源要求的网络。通过昂贵的深度数据进行监督培训的深度数据加强了问题。在这项工作中，我们提出了一个基于类似VGG05的CNN体系结构的有效的深度完成模型，并提出了一种半监督的域适应方法，以将知识从合成到现实世界数据转移，以提高数据效应并减少对大型数据库的需求。为了提高空间连贯性，我们使用分割作为其他信息来源指导学习过程。在Kitti数据集上评估了我们方法的效率和准确性。我们的方法改善了以前的有效和低参数方法的方法，同时具有明显较低的计算足迹。
Complete depth information and efficient estimators have become vital ingredients in scene understanding for automated driving tasks. A major problem for LiDAR-based depth completion is the inefficient utilization of convolutions due to the lack of coherent information as provided by the sparse nature of uncorrelated LiDAR point clouds, which often leads to complex and resource-demanding networks. The problem is reinforced by the expensive aquisition of depth data for supervised training. In this work, we propose an efficient depth completion model based on a vgg05-like CNN architecture and propose a semi-supervised domain adaptation approach to transfer knowledge from synthetic to real world data to improve data-efficiency and reduce the need for a large database. In order to boost spatial coherence, we guide the learning process using segmentations as additional source of information. The efficiency and accuracy of our approach is evaluated on the KITTI dataset. Our approach improves on previous efficient and low parameter state of the art approaches while having a noticeably lower computational footprint.
