Keywords

Bayesian edge inference, BEI, super-resolution, recapture

Abstract

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.

Original Publication Citation

N. Toronto, B. Morse, D. Ventura, and K. Seppi, "Super-resolution via recapture and Bayesian effect modeling," in IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2388-2395, June 29.

Document Type

Peer-Reviewed Article

Publication Date

2009-06-01

Permanent URL

http://hdl.lib.byu.edu/1877/2488

Publisher

IEEE

Language

English

College

Physical and Mathematical Sciences

Department

Computer Science

Share

COinS