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.
@article{arxiv.2205.05335,
title = {Deep Depth Completion from Extremely Sparse Data: A Survey},
author = {Junjie Hu and Chenyu Bao and Mete Ozay and Chenyou Fan and Qing Gao and Honghai Liu and Tin Lun Lam},
journal= {arXiv preprint arXiv:2205.05335},
year = {2022}
}