Total Variation Restoration of Images Corrupted by Poisson Noise with Iterated Conditional Expectations
- Cite this paper as:
- Abergel R., Louchet C., Moisan L., Zeng T. (2015) Total Variation Restoration of Images Corrupted by Poisson Noise with Iterated Conditional Expectations. In: Aujol JF., Nikolova M., Papadakis N. (eds) Scale Space and Variational Methods in Computer Vision. SSVM 2015. Lecture Notes in Computer Science, vol 9087. Springer, Cham
Interpreting the celebrated Rudin-Osher-Fatemi (ROF) model in a Bayesian framework has led to interesting new variants for Total Variation image denoising in the last decade. The Posterior Mean variant avoids the so-called staircasing artifact of the ROF model but is computationally very expensive. Another recent variant, called TV-ICE (for Iterated Conditional Expectation), delivers very similar images but uses a much faster fixed-point algorithm. In the present work, we consider the TV-ICE approach in the case of a Poisson noise model. We derive an explicit form of the recursion operator, and show linear convergence of the algorithm, as well as the absence of staircasing effect. We also provide a numerical algorithm that carefully handles precision and numerical overflow issues, and show experiments that illustrate the interest of this Poisson TV-ICE variant.
KeywordsPoisson noise removal Image denoising Total variation Posterior mean Marginal conditional mean Staircasing effect Fixed-point algorithm Incomplete gamma function
Unable to display preview. Download preview PDF.