IEEE Trans Pattern Anal Mach Intell. 2023 Jul;45(7):8244-8264. doi: 10.1109/TPAMI.2022.3229090. Epub 2023 Jun 5.
Depth completion aims at predicting dense pixel-wise depth from an extremely sparse map captured from a depth sensor, e.g., LiDARs. It plays an essential role in various applications such as autonomous driving, 3D reconstruction, augmented reality, and robot navigation. Recent successes on the task have been demonstrated and dominated by deep learning based solutions. In this article, for the first time, we provide a comprehensive literature review that helps readers better grasp the research trends and clearly understand the current advances. We investigate the related studies from the design aspects of network architectures, loss functions, benchmark datasets, and learning strategies with a proposal of a novel taxonomy that categorizes existing methods. Besides, we present a quantitative comparison of model performance on three widely used benchmarks, including indoor and outdoor datasets. Finally, we discuss the challenges of prior works and provide readers with some insights for future research directions.
深度补全旨在从深度传感器（例如 LiDAR）获取的极稀疏图中预测密集的像素级深度。它在自动驾驶、3D 重建、增强现实和机器人导航等各种应用中发挥着重要作用。最近，基于深度学习的解决方案在该任务上取得了成功，并占据主导地位。在本文中，我们首次提供了全面的文献综述，帮助读者更好地掌握研究趋势，并清楚地了解当前的进展。我们从网络架构、损失函数、基准数据集和学习策略的设计方面研究了相关研究，并提出了一种新的分类法，对现有方法进行分类。此外，我们还在三个广泛使用的基准上对模型性能进行了定量比较，包括室内和室外数据集。最后，我们讨论了前人工作的挑战，并为读者提供了一些未来研究方向的见解。
