In this paper, we propose a deep learning architecture that produces accurate dense depth
for the outdoor scene from a single color image and a sparse depth. Inspired by the indoor …

Depth maps produced by LiDAR-based approaches are sparse. Even high-end LiDAR
sensors produce highly sparse depth maps, which are also noisy around the object …

The goal of our work is to complete the depth channel of an RGB-D image. Commodity-
grade depth cameras often fail to sense depth for shiny, bright, transparent, and distant …

Depth completion aims to recover dense depth maps from sparse depth measurements. It is
of increasing importance for autonomous driving and draws increasing attention from the …

Depth completion aims to recover a dense depth map from the sparse depth data and the
corresponding single RGB image. The observed pixels provide the significant guidance for …

Transparent objects are a common part of everyday life, yet they possess unique visual
properties that make them incredibly difficult for standard 3D sensors to produce accurate …

Despite significant progress made in the past few years, challenges remain for depth
estimation using a single monocular image. First, it is nontrivial to train a metric-depth …

Despite significant research focus on 3D scene capture systems, numerous unresolved
challenges remain in relation to achieving full coverage scene depth estimation which is the …

Inferring the depth of images is a fundamental inverse problem within the field of Computer
Vision since depth information is obtained through 2D images, which can be generated from …

We address the task of single depth image inpainting. Without the corresponding color
images, previous or next frames, depth image inpainting is quite challenging. One natural …