Estimating depth from single RGB images and videos is of widespread interest due to its
applications in many areas, including autonomous driving, 3D reconstruction, digital …

Estimating the accurate depth from a single image is challenging since it is inherently
ambiguous and ill-posed. While recent works design increasingly complicated and powerful …

Monocular depth estimation is fundamental for 3D scene understanding and downstream
applications. However, even under the supervised setup, it is still challenging and ill-posed …

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 …

We propose a simple, efficient, yet powerful framework for dense visual predictions based
on the conditional diffusion pipeline. Our approach follows a" noise-to-map" generative …

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 is vital for scene understanding and downstream tasks. We
focus on the supervised setup, in which ground-truth depth is available only at training time …

Neural networks have shown great abilities in estimating depth from a single image.
However, the inferred depth maps are well below one-megapixel resolution and often lack …