 |
Technical Program
Paper Detail
| Paper: | WA-P5.12 |
| Session: | Denoising - II |
| Time: | Wednesday, October 11, 09:40 - 12:20 |
| Presentation: |
Poster
|
| 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. |
|
