Event Location: NSH 1507
Bio: Larry Zitnick received the PhD degree in robotics from Carnegie
Mellon University in 2003. His thesis focused on algorithms for
efficiently computing conditional probabilities in large-problem domains.
Previously, his work centered on stereo vision, including cooperative and
parallel algorithms, as well as developing a portable 3D camera.
Currently, he is a researcher at the Interactive Visual Media group at
Microsoft Research. His latest work includes spatial and temporal video
interpolation, object recognition, and computational photography.

Abstract: We present a framework for automatically enhancing videos of a static
scene by capturing a few photographs of the same scene. We demonstrate
the transfer of photographic qualities such as high resolution, high
dynamic range and better lighting from the photographs to the video.
Additionally, users may edit videos using photo-editing techniques that
are propagated through the video, including editing and removing objects.
These capabilities are enabled by two technical contributions presented in
this talk. First, we make several improvements to a state-of-the-art
multiview stereo algorithm in order to compute view-dependent depths using
video, photographs, and structure-from-motion data. Second, we present a
novel image-based rendering algorithm that can re-render the input video
using the appearance of the photographs while preserving certain temporal
dynamics from the video, such as specularities and dynamic scene lighting.