Sciweavers

CVPR
2009
IEEE

Super-Resolution via Recapture and Bayesian Effect Modeling

14 years 10 months ago
Super-Resolution via Recapture and Bayesian Effect Modeling
This paper presents Bayesian edge inference (BEI), a single-frame super-resolution method explicitly grounded in Bayesian inference that addresses issues common to existing methods. Though the best give excellent results at modest magnification factors, they suffer from gradient stepping and boundary coherence problems by factors of 4x. Central to BEI is a causal framework that allows image capture and recapture to be modeled differently, a principled way of undoing downsampling blur, and a technique for incorporating Markov random field potentials arbitrarily into Bayesian networks. Besides addressing gradient and boundary issues, BEI is shown to be competitive with existing methods on published correctness measures. The model and framework are shown to generalize to other reconstruction tasks by demonstrating BEI’s effectiveness at CCD demosaicing and inpainting with only trivial changes.
Bryan S. Morse, Dan Ventura, Kevin D. Seppi, Neil
Added 09 May 2009
Updated 10 Dec 2009
Type Conference
Year 2009
Where CVPR
Authors Bryan S. Morse, Dan Ventura, Kevin D. Seppi, Neil Toronto
Comments (0)