Learning Iterative Image Reconstruction in the Neural Abstraction
Pyramid
-
Author: Sven Behnke
-
International Journal of Computational Intelligence and Applications, Special
Issue on Neural Networks at IJCAI-2001, vol. 1, no. 4, pp. 427-438, 2001.
-
Abstract:
Successful image reconstruction requires the recognition of a scene
and the generation of a clean image of that scene. We propose to use recurrent
neural networks for both analysis and synthesis.
The networks have a hierarchical architecture that represents images
in multiple scales with dif-ferent degrees of abstraction. The mapping
between these representations is mediated by a local connection structure.
We supply the networks with degraded images and train them to reconstruct
the originals iteratively. This iterative reconstruction makes it possible
to use partial results as context information to resolve ambiguities.
We demonstrate the power of the approach using three examples: superresolution,
fill-in of occluded parts, and noise removal / contrast enhancement. We
also reconstruct images from sequences of degraded images.
-
Keywords: Neural Abstraction Pyramid, Image Reconstruction, Backpropagation
Through Time, Superresolution, Occlusion, Contrast Enhancement
-
Full paper: ijcia01.pdf
back
to selected image interpretation publications