ErA: Error-Aware Deep Unrolling Network for Single Image Defocus Deblurring
Tu Vo, Chan Y. Park
eess.IV cs.CV
Abstract
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.
Topics
Classified with taxonomy v2 on Sat, 5 Sept 2026.