In current decades, significant advancements in robotics engineering and autonomous
vehicles have improved the requirement for precise depth measurements. Depth estimation …

This paper tackles the problem of depth estimation from a single image. Existing work either
focuses on generalization performance disregarding metric scale, ie relative depth …

Abstract Monocular Depth Estimation (MDE) aims to predict pixel-wise depth given a single
RGB image. For both, the convolutional as well as the recent attention-based models …

We address the problem of estimating a high quality dense depth map from a single RGB
input image. We start out with a baseline encoder-decoder convolutional neural network …

Monocular depth estimation (MDE) is a fundamental task in computer vision and has drawn
increasing attention. Recently, some methods reformulate it as a classification-regression …

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 …

Monocular depth estimation (MDE) is a fundamental topic of geometric computer vision and
a core technique for many downstream applications. Recently, several methods reframe the …

Monocular depth estimation has drawn widespread attention from the vision community due
to its broad applications. In this paper, we propose a novel physics (geometry)-driven deep …

Depth estimation from a single image is an important task that can be applied to various
fields in computer vision, and has grown rapidly with the development of convolutional …

We propose a novel architecture for depth estimation from a single image. The architecture
itself is based on the popular encoder-decoder architecture that is frequently used as a …