In this paper, a novel convolutional neural network (CNN)-based framework is developed for
light field reconstruction from a sparse set of views. We indicate that the reconstruction can …

Per-view disparity estimation for light field (LF) is critical for various applications such as light
field editing, but previous work mostly focuses on estimating disparity for the center view. In …

We present an image-based rendering system to viewpoint-navigate through space and
time of complex real-world, dynamic scenes. Our approach accepts unsynchronized …

This paper proposes a novel real-time method for high-quality view interpolation from light
field. The proposal is a lightweight method, which can be used with consumer GPU …

Reality: The final frontier. Since the early beginnings of computer graphics, creating
authentic models of real-world objects and achieving visual realism have been major goals …

This paper proposes a novel solution of real-time depth range and correct focusing
estimation in light field videos represented by arrays of video sequences. This solution …

We present a no-reference image quality metric for image interpolation. The approach is
capable of detecting blurry regions as well as ghosting artifacts, eg, in image based …

Space-time visual effects play an increasingly prominent role in recent motion picture
productions as well as TV commercials. Currently, these effects must be meticulously …

We present an algorithm for scene flow reconstruction from multi-view data. The main
contribution is its ability to cope with asynchronously captured videos. Our holistic approach …

The ability to produce dynamic Depth of Field effects in live video streams was until recently
a quality unique to movie cameras. In this paper, we present a computational camera …