提出一种自适应修正模糊核误差的单图散焦去模糊方法。

ErA: Error-Aware Deep Unrolling Network for Single Image Defocus Deblurring

• 通过交替更新与残差网络，动态修正模糊核估计误差
• 在DPDD、RealDOF、RTF数据集上达当前最佳性能
• 无需真实标签即可在CUHK数据集上保持强泛化能力

我们提出ErA（Error-Aware Deep Unrolling Network），一种端到端的单图像散焦去模糊框架。ErA联合学习紧凑的核基底与像素级权重，同时在增强拉格朗日迭代中引入误差感知项，通过交替更新和ResUNet去噪器校正核估计误差。该方法在DPDD、RealDOF和RTF数据集上达到最优的PSNR/SSIM指标，并在无真实标签的CUHK数据集上展现出优异的泛化能力。

原文摘要 · Abstract (English)

We introduce ErA (Error-Aware Deep Unrolling Network), an end-to-end frame work for single-image defocus deblurring. ErA jointly learns a compact kerne basis and per-pixel weights, while an error-aware term in Augmented Lagrangian unrolling corrects kernel estimation errors via alternating updates and ResUNet denoisers. It achieves state-of-the-art PSNR/SSIM on DPDD, RealDOF, and RTF, and shows strong generalization on CUHK without ground truth.

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。