Autonomous vehicles were experiencing rapid development in the past few years. However,
achieving full autonomy is not a trivial task, due to the nature of the complex and dynamic …

Depth completion aims at predicting dense pixel-wise depth from an extremely sparse map
captured from a depth sensor, eg, LiDARs. It plays an essential role in various applications …

Lidar-based sensing drives current autonomous vehicles. Despite rapid progress, current
Lidar sensors still lag two decades behind traditional color cameras in terms of resolution …

Self-supervised monocular depth estimation networks are trained to predict scene depth
using nearby frames as a supervision signal during training. However, for many …

Image guided depth completion is the task of generating a dense depth map from a sparse
depth map and a high quality image. In this task, how to fuse the color and depth modalities …

This paper aims to address the problem of supervised monocular depth estimation. We start
with a meticulous pilot study to demonstrate that the long-range correlation is essential for …

Self-supervised monocular depth estimation is an attractive solution that does not require
hard-to-source depth la-bels for training. Convolutional neural networks (CNNs) have …

In this paper, we propose a robust and efficient end-to-end non-local spatial propagation
network for depth completion. The proposed network takes RGB and sparse depth images …

The success of monocular depth estimation relies on large and diverse training sets. Due to
the challenges associated with acquiring dense ground-truth depth across different …

Self-supervised monocular depth estimation presents a powerful method to obtain 3D scene
information from single camera images, which is trainable on arbitrary image sequences …