Computer Graphics
TU Braunschweig

Belief propagation optical flow for high-resolution image morphing

Belief propagation optical flow for high-resolution image morphing

Over the last decade, considerable progress has been made on the so-called early vision problems. We present an optical flow algorithm for image morphing that incorporates recent advances in feature matching, energy minimization, stereo vision and image segmentation.

At the core of our flow 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 flows possible. We detect occluded areas by evaluating the symmetry of the flow fields, we further apply Geodesic matting to automatically inpaint these regions.

Author(s):Christian Lipski, Christian Linz, Marcus Magnor
Published:August 2010
Type:Article in conference proceedings
Presented at:SIGGRAPH
Note:SIGGRAPH '10: ACM SIGGRAPH 2010 Posters
Project(s): Virtual Video Camera 

  title = {Belief propagation optical flow for high-resolution image morphing},
  author = {Lipski, Christian and Linz, Christian and Magnor, Marcus},
  booktitle = {Proc. {SIGGRAPH}},
  organization = {{ACM}},
  note = {{SIGGRAPH} '10: {ACM} {SIGGRAPH} 2010 Posters},
  pages = {1},
  month = {Aug},
  year = {2010}