Depth estimation is a classic task in computer vision, which is of great significance for many
applications such as augmented reality, target tracking and autonomous driving. Traditional …

Deep Neural Networks (DNNs) trained on one dataset (source domain) do not perform well
on another set of data (target domain), which is different but has similar properties as the …

Deep learning has produced state-of-the-art results for a variety of tasks. While such
approaches for supervised learning have performed well, they assume that training and …

Per-pixel ground-truth depth data is challenging to acquire at scale. To overcome this
limitation, self-supervised learning has emerged as a promising alternative for training …

There is a strong incentive to develop versatile learning techniques that can transfer the
knowledge of class-separability from a labeled source domain to an unlabeled target …

Estimating depth from RGB images is a long-standing ill-posed problem, which has been
explored for decades by the computer vision, graphics, and machine learning communities …

Monocular depth estimation has become one of the most studied applications in computer
vision, where the most accurate approaches are based on fully supervised learning models …

In this paper, we propose a novel Pattern-Affinitive Propagation (PAP) framework to jointly
predict depth, surface normal and semantic segmentation. The motivation behind it comes …

Unsupervised domain adaptation (DA) has gained substantial interest in semantic
segmentation. However, almost all prior arts assume concurrent access to both labeled …

Depth completion aims to recover a dense depth map from the sparse depth data and the
corresponding single RGB image. The observed pixels provide the significant guidance for …