Learnable Blur Kernel for Single-Image Defocus Deblurring in the Wild

TL;DR

This paper introduces a novel unsupervised defocus deblurring method using a learnable blur kernel and a GAN, achieving state-of-the-art perceptual quality in single-image defocus deblurring.

Contribution

It proposes a learnable blur kernel for defocus map estimation and a GAN-based approach for high-quality deblurring, both unsupervised and effective in real-world scenarios.

Findings

Achieves state-of-the-art perceptual quality with PSNR 25.56 dB and LPIPS 0.111.

Learnable blur kernel produces defocus maps comparable to supervised methods.

Method significantly improves perceptual quality in defocus deblurring tasks.

Abstract

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.