GAN Based Image Deblurring Using Dark Channel Prior
This work addresses image deblurring for applications like photography or computer vision, but it is incremental as it builds on existing GAN and prior methods.
The paper tackles image deblurring by proposing a conditional GAN tailored for this task, incorporating a modified dark channel prior into the loss function, and it shows improved performance and robustness on synthetic and natural images with a lightweight network structure.
A conditional general adversarial network (GAN) is proposed for image deblurring problem. It is tailored for image deblurring instead of just applying GAN on the deblurring problem. Motivated by that, dark channel prior is carefully picked to be incorporated into the loss function for network training. To make it more compatible with neuron networks, its original indifferentiable form is discarded and L2 norm is adopted instead. On both synthetic datasets and noisy natural images, the proposed network shows improved deblurring performance and robustness to image noise qualitatively and quantitatively. Additionally, compared to the existing end-to-end deblurring networks, our network structure is light-weight, which ensures less training and testing time.