Learnable Blur Kernel for Single-Image Defocus Deblurring in the Wild
This addresses defocus deblurring for image processing applications, offering an unsupervised alternative to dual-pixel methods, but it is incremental as it builds on existing defocus map and GAN approaches.
The paper tackles single-image defocus deblurring by proposing a method with a learnable blur kernel for unsupervised defocus map estimation and a generative adversarial network (DefocusGAN), achieving state-of-the-art results with PSNR of 25.56 dB and LPIPS of 0.111.
Recent research showed that the dual-pixel sensor has made great progress in defocus map estimation and image defocus deblurring. However, extracting real-time dual-pixel views is troublesome and complex in algorithm deployment. Moreover, the deblurred image generated by the defocus deblurring network lacks high-frequency details, which is unsatisfactory in human perception. To overcome this issue, we propose a novel defocus deblurring method that uses the guidance of the defocus map to implement image deblurring. The proposed method consists of a learnable blur kernel to estimate the defocus map, which is an unsupervised method, and a single-image defocus deblurring generative adversarial network (DefocusGAN) for the first time. The proposed network can learn the deblurring of different regions and recover realistic details. We propose a defocus adversarial loss to guide this training process. Competitive experimental results confirm that with a learnable blur kernel, the generated defocus map can achieve results comparable to supervised methods. In the single-image defocus deblurring task, the proposed method achieves state-of-the-art results, especially significant improvements in perceptual quality, where PSNR reaches 25.56 dB and LPIPS reaches 0.111.