Non-blind Image Restoration Based on Convolutional Neural Network
This work addresses a specific issue in image restoration for applications requiring robustness to model variations, but it is incremental as it builds on existing CNN-based approaches.
The paper tackles the problem of blind image restoration processors being too sensitive to degradation model perturbations by proposing a non-blind CNN-based processor that is more robust, with experimental comparisons showing it can robustly restore images compared to existing blind methods.
Blind image restoration processors based on convolutional neural network (CNN) are intensively researched because of their high performance. However, they are too sensitive to the perturbation of the degradation model. They easily fail to restore the image whose degradation model is slightly different from the trained degradation model. In this paper, we propose a non-blind CNN-based image restoration processor, aiming to be robust against a perturbation of the degradation model compared to the blind restoration processor. Experimental comparisons demonstrate that the proposed non-blind CNN-based image restoration processor can robustly restore images compared to existing blind CNN-based image restoration processors.