Multi-image interpolation based on graph-cuts and symmetric optical flow

Multi-image interpolation in space and time has recently received
considerable attention. Typically, the interpolated image is synthesized
by adaptively blending several forward-warped images.
Blending itself is a low-pass filtering operation: the interpolated images
are prone to blurring and ghosting artifacts as soon as the underlying
correspondence fields are imperfect. We address both issues
and propose a multi-image interpolation algorithm that avoids
blending. Instead, our algorithm decides for each pixel in the synthesized
view from which input image to sample. Combined with
a symmetrical long-range optical flow formulation for correspondence
field estimation, our approach yields crisp interpolated images
without ghosting artifacts.
Author(s): | Christian Linz, Christian Lipski, Marcus Magnor |
---|---|
Published: | August 2010 |
Type: | Article in conference proceedings |
Book: | Proc. SIGGRAPH (ACM) |
Presented at: | SIGGRAPH |
Note: | SIGGRAPH '10: ACM SIGGRAPH 2010 Posters |
Project(s): | Image-space Editing of 3D Content |
@inproceedings{linz10SIGposter, title = {Multi-image interpolation based on graph-cuts and symmetric optical flow}, author = {Linz, Christian and Lipski, Christian and Magnor, Marcus}, booktitle = {Proc. {SIGGRAPH}}, organization = {{ACM}}, note = {{SIGGRAPH} '10: {ACM} {SIGGRAPH} 2010 Posters}, pages = {1}, month = {Aug}, year = {2010} }
Authors
Christian Linz
Fmr. ResearcherChristian Lipski
Fmr. Senior ResearcherMarcus Magnor
Director, Chair