Multi-fidelity and learning-regularization for single image super resolution
From MaRDI portal
The new approach to super-resolution ill-posed problem is proposed using regularization. A~multi-fidelity term is employed to measure the similarities between the observed data and the simulated data. The restoration procedure is decomposed into regularization-based super-resolution problem's solver and a denoising problem's solver. The effectiveness of the proposed method is validated using both synthetic and real-world low resolution test images.
Recommendations
- Multi-frame super resolution via deep plug-and-play CNN regularization
- A total fractional-order variation model for image super-resolution and its SAV algorithm
- A multi-frame super-resolution based on new variational data fidelity term
- Image super-resolution reconstruction based on Dirac residual
- Single image super-resolution via non-local normalized graph Laplacian regularization: a self-similarity tribute
Cites work
- An edge preserving high-order PDE for multiframe image super-resolution
- High-quality Image Restoration Using Low-Rank Patch Regularization and Global Structure Sparsity
- Robust Single-Image Super-Resolution Based on Adaptive Edge-Preserving Smoothing Regularization
- Unified Single-Image and Video Super-Resolution via Denoising Algorithms
Cited in
(22)- Single image super-resolution by approximated Heaviside functions
- A multi-frame super-resolution based on new variational data fidelity term
- Distributed reconstruction of time-varying graph signals via a modified Newton's method
- An improved bilevel optimization approach for image super-resolution based on a fractional diffusion tensor
- Multi-frame super resolution via deep plug-and-play CNN regularization
- Single image super-resolution via non-local normalized graph Laplacian regularization: a self-similarity tribute
- Multi-example feature-constrained back-projection method for image super-resolution
- Single image super-resolution via blind blurring estimation and anchored space mapping
- Single image super-resolution by non-linear sparse representation and support vector regression
- Determining the regularization parameters for super-resolution problems
- Example-based single document image super-resolution: a global MAP approach with outlier rejection
- Superresolution from a single noisy image by the median filter transform
- Resolution Enhancement in $\Sigma\Delta$ Learners for Superresolution Source Separation
- Learning Super-Resolution Jointly From External and Internal Examples
- Single Image Super-Resolution Using Global Regression Based on Multiple Local Linear Mappings
- scientific article; zbMATH DE number 7366652 (Why is no real title available?)
- scientific article; zbMATH DE number 7365699 (Why is no real title available?)
- A single-image super-resolution algorithm based on multi-scale nonlocal regularization
- Single image super-resolution reconstruction based on multi-feature fusion
- Efficient and effective total variation image super-resolution: a preconditioned operator splitting approach
- Learning nonlocal weights for second-order nonlocal super-resolution
- A linear well-posed solution to recover high-frequency information for super resolution image reconstruction
This page was built for publication: Multi-fidelity and learning-regularization for single image super resolution
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2148464)
