Recent years have witnessed enormous progress in AI-related fields such as computer
vision, machine learning, and autonomous vehicles. As with any rapidly growing field, it …

Self-supervised paradigms for monocular depth estimation are very appealing since they do
not require ground truth annotations at all. Despite the astonishing results yielded by such …

Establishing dense correspondences between a pair of images is an important and general
problem. However, dense flow estimation is often inaccurate in the case of large …

Optical flow estimation can be formulated as an end-to-end supervised learning problem,
which yields estimates with a superior accuracy-runtime tradeoff compared to alternative …

Establishing robust and accurate correspondences between a pair of images is a long-
standing computer vision problem with numerous applications. While classically dominated …

We present a supervised learning-based method to estimate a per-pixel confidence for
optical flow vectors. Regions of low texture and pixels close to occlusion boundaries are …

Establishing dense correspondences across semantically similar images remains a
challenging task due to the significant intra-class variations and background clutters …

Optical flow estimation remains challenging due to untextured areas, motion boundaries,
occlusions, and more. Thus, the estimated flow is not equally reliable across the image. To …

The objective for establishing dense correspondence between paired images consists of
two terms: a data term and a prior term. While conventional techniques focused on defining …

Streamflow variability is affected by both climate change and direct human impacts within
the catchment. Quantification of the role of these two factors have significant implications for …