Deep Robust Image Restoration Using the Moore-Penrose Blur Inverse

This paper proposes a deep learning model for robust image restoration when the degradation is not precisely known. We show how the Moore-Penrose pseudo-inverse of a blur convolution operator can be approximated by a Wiener filter's impulse response. The image restoration problem is then cast a...

Full description

Saved in:
Bibliographic Details
Published in2023 IEEE International Conference on Image Processing (ICIP) pp. 775 - 779
Main Authors Lopez-Tapia, Santiago, Mateos, Javier, Molina, Rafael, Katsaggelos, Aggelos K.
Format Conference Proceeding
LanguageEnglish
Published IEEE 08.10.2023
Subjects
Analytical models
Convolution
Deep learning
Degradation
Estimation error
Moore-Penrose pseudo-inverse
Robust image restoration
Robustness
Wiener filters
Online AccessGet full text

Cover

More Information
Summary:This paper proposes a deep learning model for robust image restoration when the degradation is not precisely known. We show how the Moore-Penrose pseudo-inverse of a blur convolution operator can be approximated by a Wiener filter's impulse response. The image restoration problem is then cast as the learning of a residual on the frequencies where the blurring filter is zero which, when added to the Wiener restoration, will satisfy the image formation model. A Dynamic Filter Network removes artifacts introduced by inaccurate blur estimations and other image formation model inconsistencies. The experiments conducted on synthetic and real image datasets assert the performance and robustness of the proposed method and show its superiority to existing ones.
DOI:10.1109/ICIP49359.2023.10223181