Learning Discriminative Shrinkage Deep Networks for Image Deconvolution

  title={Learning Discriminative Shrinkage Deep Networks for Image Deconvolution},
  author={Pin-Hung Kuo and Jinshan Pan and Shao-Yi Chien and Ming-Hsuan Yang},
. Most existing methods usually formulate the non-blind deconvolution problem into a maximum-a-posteriori framework and ad-dress it by manually designing a variety of regularization terms and data terms of the latent clear images. However, explicitly designing these two terms is quite challenging and usually leads to complex optimization problems which are difficult to solve. This paper proposes an effective non-blind deconvolution approach by learning discriminative shrinkage functions to… 



Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution

The proposed fully convolutional network is able to learn an adaptive image prior, which keeps both local and global information, and performs favorably against state-of-the-art algorithms in terms of quality and speed.

Learning Deep CNN Denoiser Prior for Image Restoration

Experimental results demonstrate that the learned set of denoisers can not only achieve promising Gaussian denoising results but also can be used as prior to deliver good performance for various low-level vision applications.

Deep Priors Inside an Unrolled and Adaptive Deconvolution Model

A deblurring architecture that adopts adaptive deconvolution modules and learning based image prior solvers is proposed that can achieve a significant improvement on the convergence rate and result in an even better restoration performance.

Douglas-Rachford Networks: Learning Both the Image Prior and Data Fidelity Terms for Blind Image Deconvolution

A method called Dr-Net is presented, which does not require any such estimate and is further able to invert the effects of the blurring in blind image recovery tasks and is one of the fastest algorithms according to wall-clock times while doing so.

Deep Learning for Handling Kernel/model Uncertainty in Image Deconvolution

  • Yuesong NanHui Ji
  • Computer Science
    2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
A deep learning method for deconvolution is presented, which unrolls a total-least-squares (TLS) estimator whose relating priors are learned by neural networks (NNs), which shows that the proposed method is robust to kernel/model error.

Simultaneous Fidelity and Regularization Learning for Image Restoration

A principled algorithm within the maximum a posterior framework to tackle image restoration with a partially known or inaccurate degradation model is proposed, which demonstrates the effectiveness of the proposed model for image deconvolution with inaccurate blur kernels, deconVolution with multiple degradations and rain streak removal.

Learning Spatially-Variant MAP Models for Non-blind Image Deblurring

This work proposes a simple and effective approach to jointly learn these two terms, embedding deep neural networks within the constraints of the MAP framework, trained in an end-to-end manner, and results substantially outperform the current state of the art.

Deep Unfolding Network for Image Super-Resolution

This paper proposes an end-to-end trainable unfolding network which leverages both learningbased methods and model-based methods to super-resolve blurry, noisy images for different scale factors via a single model, while maintaining the advantages of learning- based methods.

A Machine Learning Approach for Non-blind Image Deconvolution

This work relies on a two-step procedure, but learns the second step on a large dataset of natural images, using a neural network, and shows that this approach outperforms the current state-of-the-art on aLarge dataset of artificially blurred images.

FISTA-Net: Learning a Fast Iterative Shrinkage Thresholding Network for Inverse Problems in Imaging

A model-based deep learning network, named FISTA-Net, is proposed by combining the merits of interpretability and generality of the model- based Fast Iterative Shrinkage/Thresholding Algorithm (FISTA) and strong regularization and tuning-free advantages of the data-driven neural network.