Superresolution from Occluded Scenes
We propose a Bayesian image superresolution method that estimates a high-resolution background image from a sequence of occluded observations. We assume that the occlusions have spatial and temporal continuities. Such assumptions would be plausible, for example, when satellite images are occluded by clouds or when a tourist site is obstructed by people. Although the exact inference of our model is difficult, an efficient superresolution algorithm is derived by using a variational Bayes technique. Experiments show that our superresolution method performs better than existing methods that do not assume the occlusions or that assume the occlusions but do not assume the temporal continuities of the occlusions.
KeywordsOcclusion removal image superresolution variational Bayes
Unable to display preview. Download preview PDF.
- 1.Kanemura, A., Maeda, S., Ishii, S.: Image superresolution under spatially structured noise. In: IEEE Int. Symp. Signal Processing and Information Technology, December 2007, pp. 275–280 (2007)Google Scholar
- 3.Babacan, D., Molina, R., Katsaggelos, A.: Total variation super resolution using a variational approach. In: IEEE Int. Conf. Image Process, October 2008, pp. 641–644 (2008)Google Scholar
- 4.Pickup, L.C., Capel, D.P., Roberts, S.J., Zisserman, A.: Bayesian image super-resolution, continued. In: Advances in NIPS. MIT Press, Cambridge (2006)Google Scholar
- 5.Ivanovski, Z.A., Panovski, L., Karam, L.J.: Robust super-resolution based on pixel-level selectivity. In: Visual Commun. Image Process. Proc. SPIE, vol. 6077, pp. 80–87 (2006)Google Scholar