Deblurgan: Blind Motion Deblurring Using Conditional Adversarial Networks

This paper presents Deblurgan, a novel approach for blind motion deblurring using conditional adversarial networks. Deblurgan leverages the power of adversarial training to effectively remove motion blur from images without requiring any prior knowledge of the blur kernel. The proposed method consists of two main components: a generator network that takes a blurry image as input and outputs a deblurred image, and a discriminator network that distinguishes between real and generated images. The generator network is trained to produce images that are indistinguishable from real images by the discriminator, while the discriminator is trained to identify fake images. Through this adversarial training process, Deblurgan learns to effectively remove motion blur from images. The effectiveness of the proposed method is demonstrated on a variety of real-world images, showing significant improvement in deblurring performance compared to existing methods.