Abstract | ||
---|---|---|
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.
|
Year | DOI | Venue |
---|---|---|
2009 | 10.1007/978-3-642-10684-2_3 | International Conference on Neural Information Processing |
Keywords | Field | DocType |
image superresolution,occluded scenes,exact inference,satellite image,temporal continuity,occluded observation,high-resolution background image,variational bayes technique,tourist site,occlusion removal,superresolution method,variational bayes.,bayesian image superresolution method,efficient superresolution algorithm,high resolution | Computer vision,Pattern recognition,Inference,Computer science,Artificial intelligence,Superresolution,Bayesian probability,Bayes' theorem | Conference |
Volume | ISSN | Citations |
5864 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 3 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wataru Fukuda | 1 | 5 | 1.49 |
Atsunori Kanemura | 2 | 75 | 12.78 |
Shin-ichi Maeda | 3 | 26 | 8.11 |
Shin Ishii | 4 | 239 | 34.39 |