High Resolution Image Correspondences for Video Post-Production Lipski Christian Linz Christian Neumann Thomas Wacker Markus Magnor Marcus 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 (Scale-Invariant Feature Transform) 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 determine plausible values in these regions. Belief Propagation Dense Image Correspondences Depth Reconstruction Optical Flow Video Post-Production 004 periodical academic journal JVRB - Journal of Virtual Reality and Broadcasting 9(2012) 8 2012 1860-2037 urn:nbn:de:0009-6-35543 10.20385/1860-2037/9.2012.8 http://nbn-resolving.de/urn:nbn:de:0009-6-35543 lipski2012