Image Zoom Completion

Abstract : We consider the problem of recovering a high-resolution image from a pair consisting of a complete low-resolution image and a high-resolution but incomplete one. We refer to this task as the image zoom completion (IZC) problem. After discussing possible contexts in which this setting may arise, we study three regularization strategies, giving full details concerning the numerical optimization of the corresponding energies, and discussing the benefits and shortcomings of each method. As the application that leads us to consider the IZC setting concerns images with strong textural content, we evaluate the performance of the proposed methods on a set of Brodatz textures, comparing the results we get with those obtained with two recent state-of-the-art single-image super-resolution algorithms.
Document type :
Journal articles
Complete list of metadatas

Cited literature [42 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01253124
Contributor : Mireille El Gheche <>
Submitted on : Monday, May 30, 2016 - 10:59:21 AM
Last modification on : Wednesday, October 9, 2019 - 1:37:52 AM

File

Hidane_2016_fv.pdf
Files produced by the author(s)

Identifiers

Citation

Moncef Hidane, Mireille El Gheche, Jean-François Aujol, Yannick Berthoumieu, Charles Deledalle. Image Zoom Completion. IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2016, 25 (8), pp.3505-3517. ⟨10.1109/TIP.2016.2571061⟩. ⟨hal-01253124v2⟩

Share

Metrics

Record views

563

Files downloads

703