Most modern consumer-grade cameras are often equipped with a rolling shutter
mechanism, which is becoming increasingly important in computer vision, robotics and …

Joint rolling shutter correction and deblurring (RSCD) techniques are critical for the
prevalent CMOS cameras. However, current approaches are still based on conventional …

Motion blurry images challenge many computer vision algorithms, eg, feature detection,
motion estimation, or object recognition. Deep convolutional neural networks are state-of-the …

Most present-day imaging devices are equipped with CMOS sensors. Motion blur is a
common artifact in hand-held cameras. Because CMOS sensors mostly employ a rolling …

We propose a generic depth-refinement scheme based on GeoNet, a recent deep-learning
approach for predicting depth and normals from a single color image, and extend it to be …

We introduce InFusionSurf, an innovative enhancement for neural radiance field (NeRF)
frameworks in 3D surface reconstruction using RGB-D video frames. Building upon previous …

This paper presents details of experimental tests of an approach to measure the distance to
obstacles in a hemispherical area around a vertical takeoff and landing unmanned aerial …

Most present-day imaging devices are equipped with CMOS sensors. Motion blur is a
common artifact in handheld cameras. Because CMOS sensors mostly employ a rolling …

Image processing is an inevitable tool for visual tracking. Visual object tracking is a very hot
area of research in the computer vision. Computer vision tasks include methods for …

Depth estimation is one of the fundamentals tasks in 3D imaging. In this work we present a
new method based on a weighted energy optimization to enhance depth images captured …