Boosting defocus deblurring via learning from all-in-focus images
Defocus deblurring is a challenging task due to spatially varying blur and limited aligned training data. Existing datasets suffer from insufficient scene diversity and misalignment between defocused and all-in-focus images, restricting network performance. Additionally, single-stage autoencoders often fall into local optima, causing under-recovery and artifacts. To address these problems, we propose a novel multi-stage restoration framework guided by information from a single all-in-focus image. First, rendering synthesis adds defocus attributes to all-in-focus images, solving data alignment and consistency issues. Second, a stacked autoencoder guided by defocus degree maps handles spatially varying blur hierarchically. Finally, Feature Selection and Feature Attention Modules discriminatively select valuable information and transmit first-stage features to later stages for better region-wise deblurring. Extensive experiments on multiple test sets validate that our method achieves state-of-the-art performance both quantitatively and qualitatively. Specifically, on the DPDD dataset, our method achieves 29.41 dB PSNR and 0.886 SSIM, outperforming the previous best method by 0.19 dB; on the RealDOF dataset, it achieves 23.65 dB PSNR, surpassing IFANet by 0.89 dB.