Modern deep learning methods constitute incredibly powerful tools to tackle a myriad of
challenging problems. However, since deep learning methods operate as black boxes, the …

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 …

Humans can easily imagine the complete 3D geometry of occluded objects and scenes. This
appealing ability is vital for recognition and understanding. To enable such capability in AI …

The visual world can be parsimoniously characterized in terms of distinct entities with sparse
interactions. Discovering this compositional structure in dynamic visual scenes has proven …

Stereo depth estimation relies on optimal correspondence matching between pixels on
epipolar lines in the left and right images to infer depth. In this work, we revisit the problem …

Depth estimation from monocular images is pivotal for real-world visual perception systems.
While current learning-based depth estimation models train and test on meticulously curated …

Despite impressive performance for high-level downstream tasks, self-supervised pre-
training methods have not yet fully delivered on dense geometric vision tasks such as stereo …

In this paper, we propose a practical three-dimensional (3D) real-scene reconstruction
framework named Deep3D, which is paired with a deep learning based multi-view stereo …

Deep learning-based stereo matching methods have made remarkable progress in recent
years. However, it is still a challenging task to achieve high accuracy in real time. In …

Monocular depth estimation is known as an ill-posed task that objects in a 2D image usually
do not contain sufficient information to predict their depth. Thus, it acts differently from other …