Backtracking-based iterative regularization method for image compressive sensing recovery
Summary: This paper presents a variant of the iterative shrinkage-thresholding (IST) algorithm, called backtracking-based adaptive IST (BAIST), for image compressive sensing (CS) reconstruction. For increasing iterations, IST usually yields a smoothing of the solution and runs into prematurity. To add back more details, the BAIST method backtracks to the previous noisy image using L2 norm minimization, i.e., minimizing the Euclidean distance between the current solution and the previous ones. Through this modification, the BAIST method achieves superior performance while maintaining the low complexity of IST-type methods. Also, BAIST takes a nonlocal regularization with an adaptive regularizor to automatically detect the sparsity level of an image. Experimental results show that our algorithm outperforms the original IST method and several excellent CS techniques.
- Image compressive sensing reconstruction based on low-rank and total variation regularization
- A compressed sensing image reconstruction algorithm based on non-local regularization
- Hessian Schatten-norm and adaptive dictionary for image recovery
- An image reconstruction algorithm of compressed sensing based on nonlocal similarity model
- scientific article; zbMATH DE number 7028997
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- An iterative thresholding algorithm for linear inverse problems with a sparsity constraint
- Compressive Imaging Using Approximate Message Passing and a Markov-Tree Prior
- Compressive Sensing via Nonlocal Low-Rank Regularization
- Fast Image Recovery Using Variable Splitting and Constrained Optimization
- From Denoising to Compressed Sensing
This page was built for publication: Backtracking-based iterative regularization method for image compressive sensing recovery
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1662590)
