Integrating neural networks into the blind deblurring framework to compete with the end-to-end learning-based methods
This work addresses image restoration for computer vision applications, but it is incremental as it builds on existing frameworks.
The paper tackles the problem of blind deblurring by integrating neural networks into a conventional framework to address drawbacks of end-to-end learning-based methods, such as poor performance with complex motion and unreasonable results, resulting in restored details and better generalization ability compared to state-of-the-art methods.
Recently, end-to-end learning-based methods based on deep neural network (DNN) have been proven effective for blind deblurring. Without human-made assumptions and numerical algorithms, they are able to restore images with fewer artifacts and better perceptual quality. However, in practice, we also find some of their drawbacks. Without the theoretical guidance, these methods can not perform well when the motion is complex and sometimes generate unreasonable results. In this paper, for overcoming these drawbacks, we integrate deep convolution neural networks into conventional deblurring framework. Specifically, we build Stacked Estimation Residual Net (SEN) to estimate the motion flow map and Recurrent Prior Generative and Adversarial Net (RP-GAN) to learn the implicit image prior in the optimization model. Comparing with state-of-the-art end-to-end learning-based methods, our method restores reasonable details and shows better generalization ability.