Differential methods belong to the most widely used techniques for optic flow computation in
image sequences. They can be classified into local methods such as the Lucas–Kanade …

Dense motion estimations obtained from optical flow techniques play a significant role in
many image processing and computer vision tasks. Remarkable progress has been made in …

Assumptions of brightness constancy and spatial smoothness underlie most optical flow
estimation methods. In contrast to standard heuristic formulations, we learn a statistical …

We present an analysis of the spatial and temporal statistics of “natural” optical flow fields
and a novel flow algorithm that exploits their spatial statistics. Training flow fields are …

Current deep neural network approaches for camera pose estimation rely on scene structure
for 3D motion estimation, but this decreases the robustness and thereby makes cross …

Event-based cameras have been designed for scene motion perception-their high temporal
resolution and spatial data sparsity converts the scene into a volume of boundary …

The task of image registration is fundamental in image processing. It often is a critical
preprocessing step to many modern image processing and computer vision tasks, and many …

Convolutional neural networks (CNNs) are increasingly adopted in medical imaging, eg, to
reconstruct high-quality images from undersampled magnetic resonance imaging (MRI) …

Recently, several methods that measure the velocity of magnetized plasma from time series
of photospheric vector magnetograms have been developed. Velocity fields derived using …

To solve the general point correspondence problem in which the underlying transformation
between image patches is represented by a homography, a solution based on extensive use …