论文标题
通过KISS-GP进行稠密深度推理和稀疏范围测量之间的平衡深度完成
Balanced Depth Completion between Dense Depth Inference and Sparse Range Measurements via KISS-GP
论文作者
论文摘要
估计密集而准确的深度图是自动驾驶和机器人技术的关键要求。深度学习的最新进展允许从单个图像完全分辨出深度估计。尽管取得了令人印象深刻的结果，但许多基于深度学习的单眼深度估计（MDE）算法仍未保持其准确性产生仪表级估计误差。在许多机器人技术应用中，光检测和范围（LIDAR）很容易获得准确但稀疏的测量结果。尽管它们非常准确，但稀疏性限制了完整的分辨率深度图重建。针对密集和准确的深度图恢复问题，本文通过划分深度推理和深度回归的作用，将这两种方式作为深度完成（DC）问题融合。利用最先进的MDE和基于高斯过程（GP）的深度回归方法，我们提出了一种通用解决方案，可以通过稀疏的范围测量来增强其深度来灵活地与各种MDE模块一起使用。为了克服GP的主要局限性，我们采用可伸缩结构化（KISS）-GP的内核插值，并减轻O（n^3）到O（n）的计算复杂性。我们的实验表明，我们方法的准确性和鲁棒性优于最先进的无监督方法，用于稀疏和有偏见的测量。
Estimating a dense and accurate depth map is the key requirement for autonomous driving and robotics. Recent advances in deep learning have allowed depth estimation in full resolution from a single image. Despite this impressive result, many deep-learning-based monocular depth estimation (MDE) algorithms have failed to keep their accuracy yielding a meter-level estimation error. In many robotics applications, accurate but sparse measurements are readily available from Light Detection and Ranging (LiDAR). Although they are highly accurate, the sparsity limits full resolution depth map reconstruction. Targeting the problem of dense and accurate depth map recovery, this paper introduces the fusion of these two modalities as a depth completion (DC) problem by dividing the role of depth inference and depth regression. Utilizing the state-of-the-art MDE and our Gaussian process (GP) based depth-regression method, we propose a general solution that can flexibly work with various MDE modules by enhancing its depth with sparse range measurements. To overcome the major limitation of GP, we adopt Kernel Interpolation for Scalable Structured (KISS)-GP and mitigate the computational complexity from O(N^3) to O(N). Our experiments demonstrate that the accuracy and robustness of our method outperform state-of-the-art unsupervised methods for sparse and biased measurements.
