High Resolution Image Correspondences for Video Post-Production Christian Lipski, Christian Linz, Thomas Neumann, Markus Wacker, Marcus Magnor

Christian Lipski, Christian Linz, Thomas Neumann, Markus Wacker, and Marcus Magnor: "High Resolution Image Correspondences for Video Post-Production", in Proc. European Conference on Visual Media Production (CVMP), Los Alamitos, CA, USA, vol. 7, pp. 33–39, IEEE Computer Society, November 2010. http://doi.ieeecomputersociety.org/10.1109/CVMP.2010.12 Part of project "Virtual Video Camera". [pdf] [bib]

Abstract

We present an algorithm for estimating dense image
correspondences. Our versatile approach lends itself to
various tasks typical for video post-processing, including
image morphing, optical flow estimation, stereo rectification,
disparity/depth reconstruction and baseline adjustment. We
incorporate recent advances in feature matching, energy
minimization, stereo vision and data clustering into our
approach. At the core of our correspondence estimation we
use Efficient Belief Propagation for energy minimization.
While state-of-the-art algorithms only work on thumbnail-sized
images, our novel feature downsampling scheme
in combination with a simple, yet efficient data term
compression can cope with high-resolution data. The
incorporation of SIFT features into data term computation
further resolves matching ambiguities, making long-range
correspondence estimation possible. We detect occluded
areas by evaluating the correspondence symmetry, we further
apply Geodesic matting to automatically inpaint these regions.

TU Braunschweig - Fakultät für Mathematik und Informatik - Computer Graphics - Publications - High Resolution Image Correspondences for Video Post-Production