Synthetic datasets, for which we propose the term synthsets, are not a novelty but have
become a necessity. Although they have been used in computer vision since 1989, hel** …

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 …

Indoor navigation has remained an active research area for the last decade. Unlike outdoor
environments, indoor environments have additional challenges, such as weak signals, low …

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 …

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 …

Deep learning (DL) techniques have obtained remarkable achievements on various tasks,
such as image recognition, object detection, and language modeling. However, building a …

For many fundamental scene understanding tasks, it is difficult or impossible to obtain per-
pixel ground truth labels from real images. We address this challenge by introducing …

We release MiDaS v3. 1 for monocular depth estimation, offering a variety of new models
based on different encoder backbones. This release is motivated by the success of …

Real-time performance of stereo matching networks is important for many applications, such
as automatic driving, robot navigation and augmented reality (AR). Although significant …