Transformers have demonstrated impressive expressiveness and transfer capability in
computer vision fields. Dense prediction is a fundamental problem in computer vision that is …

Vision Transformers (ViTs) are becoming more popular and dominating technique for
various vision tasks, compare to Convolutional Neural Networks (CNNs). As a demanding …

Estimating 3D human poses from monocular videos is a challenging task due to depth
ambiguity and self-occlusion. Most existing works attempt to solve both issues by exploiting …

Monocular depth estimation is a fundamental computer vision task. Recovering 3D depth
from a single image is geometrically ill-posed and requires scene understanding so it is not …

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 …

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 …

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 …

Self-supervised monocular depth estimation is an attractive solution that does not require
hard-to-source depth la-bels for training. Convolutional neural networks (CNNs) have …

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 …