We review solutions to the problem of depth estimation, arguably the most important subtask
in scene understanding. We focus on the single image depth estimation problem. Due to its …

Abstract This work presents Depth Anything a highly practical solution for robust monocular
depth estimation. Without pursuing novel technical modules we aim to build a simple yet …

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 …

Reconstructing accurate 3D scenes from images is a long-standing vision task. Due to the ill-
posedness of the single-image reconstruction problem, most well-established methods are …

We introduce dense prediction transformers, an architecture that leverages vision
transformers in place of convolutional networks as a backbone for dense prediction tasks …

Neural network based computer vision systems are typically built on a backbone, a
pretrained or randomly initialized feature extractor. Several years ago, the default option was …

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 …

Despite significant progress in monocular depth estimation in the wild, recent state-of-the-art
methods cannot be used to recover accurate 3D scene shape due to an unknown depth shift …

We present a foundation model for zero-shot metric monocular depth estimation. Our model,
Depth Pro, synthesizes high-resolution depth maps with unparalleled sharpness and high …