ErA: Error-Aware Deep Unrolling Network for Single Image Defocus Debluring
Tu Vo ⋅ Chan Youn Park
2025 Poster
in
Workshop: Constrained Optimization for Machine Learning
in
Workshop: Constrained Optimization for Machine Learning
Abstract
We introduce ErA (Error-Aware Deep Unrolling Network), an end-to-end framework for single-image defocus deblurring. ErA jointly learns a compact kernel 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.
Chat is not available.
Successful Page Load