Corpus ID: 59608854

Speeding up scaled gradient projection methods using deep neural networks for inverse problems in image processing

  title={Speeding up scaled gradient projection methods using deep neural networks for inverse problems in image processing},
  author={Byung Hyun Lee and Se Young Chun},
Conventional optimization based methods have utilized forward models with image priors to solve inverse problems in image processing. Recently, deep neural networks (DNN) have been investigated to significantly improve the image quality of the solution for inverse problems. Most DNN based inverse problems have focused on using data-driven image priors with massive amount of data. However, these methods often do not inherit nice properties of conventional approaches using theoretically well… Expand
Multiple Norms and Boundary Constraint Enforced Image Deblurring via Efficient MCMC Algorithm
This letter proposes a new image deblurring algorithm, called MNBC-Gibbs (multiple norms and boundary constraint enforced Gibbs sampling), where the quadratic and sparseness-inducing norms are combined to construct regularization term, and the objective function is gradually minimized without requirement of regularization parameter choice. Expand


CNN-Based Projected Gradient Descent for Consistent CT Image Reconstruction
A relaxed version of PGD wherein gradient descent enforces measurement consistency, while a CNN recursively projects the solution closer to the space of desired reconstruction images and shows an improvement over total variation-based regularization, dictionary learning, and a state-of-the-art deep learning-based direct reconstruction technique. Expand
Gradient-Based Image Recovery Methods From Incomplete Fourier Measurements
An algorithm called GradientRec is developed that uses a CS algorithm to recover the horizontal and vertical gradients and then estimates the original image from these gradients, and presents two methods of solving the latter inverse problem, one based on least-square optimization and the other based on a generalized Poisson solver. Expand
One Network to Solve Them All — Solving Linear Inverse Problems Using Deep Projection Models
This work proposes a general framework to train a single deep neural network that solves arbitrary linear inverse problems and demonstrates superior performance over traditional methods using wavelet sparsity prior while achieving performance comparable to specially-trained networks on tasks including compressive sensing and pixel-wise inpainting. Expand
Learned D-AMP: Principled Neural Network based Compressive Image Recovery
The LDAMP network is easy to train, can be applied to a variety of different measurement matrices, and comes with a state-evolution heuristic that accurately predicts its performance, which outperforms the state-of-the-art BM3D-AMP and NLR-CS algorithms in terms of both accuracy and run time. Expand
Image Denoising and Inpainting with Deep Neural Networks
A novel approach to low-level vision problems that combines sparse coding and deep networks pre-trained with denoising auto-encoder (DA) is presented and can automatically remove complex patterns like superimposed text from an image, rather than simple patterns like pixels missing at random. Expand
Deep ADMM-Net for Compressive Sensing MRI
Experiments on MRI image reconstruction under different sampling ratios in k-space demonstrate that the proposed novel ADMM-Net algorithm significantly improves the baseline ADMM algorithm and achieves high reconstruction accuracies with fast computational speed. Expand
Deep Convolutional Neural Network for Inverse Problems in Imaging
The proposed network outperforms total variation-regularized iterative reconstruction for the more realistic phantoms and requires less than a second to reconstruct a <inline-formula> <tex-math notation="LaTeX">$512\times 512$ </tex- math></inline- formula> image on the GPU. Expand
A scaled gradient projection method for constrained image deblurring
A class of scaled gradient projection methods for optimization problems with simple constraints is considered. These iterative algorithms can be useful in variational approaches to image deblurringExpand
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
This paper investigates the construction of feed-forward denoising convolutional neural networks (DnCNNs) to embrace the progress in very deep architecture, learning algorithm, and regularization method into image Denoising, and uses residual learning and batch normalization to speed up the training process as well as boost theDenoising performance. Expand
Enhanced Deep Residual Networks for Single Image Super-Resolution
This paper develops an enhanced deep super-resolution network (EDSR) with performance exceeding those of current state-of-the-art SR methods, and proposes a new multi-scale deepsuper-resolution system (MDSR) and training method, which can reconstruct high-resolution images of different upscaling factors in a single model. Expand