Real-world defocus deblurring via score-based diffusion models.

Defocus blur commonly arises from the cameras' depth-of-field limitations. While the deep learning method shows promise for image restoration problems, defocus deblurring requires accurate training data comprising pairs of all-in-focus and defocus images, which can be difficult to collect in real-world scenarios. To address this problem, we propose a high-resolution iterative deblurring method for real scenes driven by a score-based diffusion model. The method trains a score network by learning the score function of focused images at different noise levels and reconstructs high-quality images through reverse-time stochastic differential equation (SDE). A prediction-correction (PC) framework corrects discretization errors in the reverse-time SDE to enhance the robustness of images during reconstruction. The iterative nature of diffusion models enables a gradual improvement in image quality by progressively enhancing details and refining marginal distribution with each iteration. This process allows the distribution of generated images to increasingly approximate that of sharply focused images. Unlike mainstream end-to-end approaches, this method does not require paired all-in-focus and defocus images to train the model. The real-world datasets, such as self-captured datasets, were used for model training. Additional testing was conducted on the RealBlur and DED datasets to evaluate the efficacy of the proposed method. Compared to DnCNN, FFDNet and CycleGAN, superior performance was achieved by the proposed method on real-world datasets, including self-captured scenarios, with experimental results showing improvements of approximately 13.4% in PSNR and 34.7% in SSIM. These results indicate that significant enhancement in the clarity of defocus images can be attained, effectively enabling high-resolution iterative defocus deblurring in real-world scenarios through the diffusion model.