Video Processing

This paper investigates stereoscopic window violation artifacts, which often interfere with artistic freedom and constrain the comfortable depth volume.

This paper presents an effective method for detecting potentially salient foreground regions.

In this paper we extend the basic concept of local warping for parallax removal.

We introduce the concept of a static high-resolution master camera for improved long-term multiview alignment.

Through the research frameworks of the European Commission, in particular, a number of long-term issues have been addressed to overcome limitations of the traditional two-view stereoscopy.

In this work, we analyze and compare spatially-varying image warping techniques in terms of quality and computational performance.

In this paper, we describe an efficient ASIC core that is able to detect up to 25 k interest points in real time on a 720p video stream using the recently proposed Semantic Kernels Binarized (SKB) algorithm.

In this paper, we present a computational stereo camera system that closes the control loop from capture and analysis to automatic adjustment of physical parameters.

In this work, we address sparse linear solvers for real-time video applications.

In this paper, we approach this problem by asynchronously recording local contrast change at high speed, using a type of visual capture device called a Dynamic Vision Sensor (DVS).