ICIP 2006, Atlanta, GA
 

Slide Show

Atlanta Conv. & Vis. Bureau

 

My ICIP 2006 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.

Paper Detail

Paper:WA-P5.12
Session:Denoising - II
Time:Wednesday, October 11, 09:40 - 12:20
Presentation: Poster
Topic: Image & Video Restoration and Enhancement: Denoising
Title: DENOISING ARCHIVAL FILMS USING A LEARNED BAYESIAN MODEL
Authors: Teodor Mihai Moldovan; Brown University 
 Stefan Roth; Brown University 
 Michael J. Black; Brown University 
Abstract: We develop a Bayesian model of digitized archival films and use this for denoising, or more specifically de-graining, individual frames. In contrast to previous approaches our model uses a learned spatial prior and a unique likelihood term that models the physics that generates the image grain. The spatial prior is represented by a high-order Markov random field based on the recently proposed Field-of-Experts framework. We propose a new model of the image grain in archival films based on an inhomogeneous beta distribution in which the variance is a function of image luminance. We train this noise model for a particular film and perform de-graining using a diffusion method. Quantitative results show improved signal-to-noise ratio relative to the standard ad hoc Gaussian noise model.