Blind Poissonian image deblurring regularized by a denoiser constraint and deep image prior
Image analysis in multivariate analysis (62H35) Numerical methods for inverse problems for integral equations (65R32) Computing methodologies for image processing (68U10) Nonconvex programming, global optimization (90C26) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)
Summary: The denoising and deblurring of Poisson images are opposite inverse problems. Single image deblurring methods are sensitive to image noise. A single noise filter can effectively remove noise in advance, but it also damages blurred information. To simultaneously solve the denoising and deblurring of Poissonian images better, we learn the implicit deep image prior from a single degraded image and use the denoiser as a regularization term to constrain the latent clear image. Combined with the explicit \(L_0\) regularization prior of the image, the denoising and deblurring model of the Poisson image is established. Then, the split Bregman iteration strategy is used to optimize the point spread function estimation and latent clear image estimation. The experimental results demonstrate that the proposed method achieves good restoration results on a series of simulated and real blurred images with Poisson noise.
- Poissonian image deconvolution via sparse and redundant representations and framelet regularization
- Deblurring Poisson noisy images by total variation with overlapping group sparsity
- A nonstationary accelerating alternating direction method for frame-based Poissonian image deblurring
- Non-blind and blind deconvolution under Poisson noise using fractional-order total variation
- Several nonconvex models for image deblurring under Poisson noise
- A Closed-Form Approximation of the Exact Unbiased Inverse of the Anscombe Variance-Stabilizing Transformation
- A Review of Image Denoising Algorithms, with a New One
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- Motion Blur Kernel Estimation via Deep Learning
- Optimal Inversion of the Anscombe Transformation in Low-Count Poisson Image Denoising
- Optimal Inversion of the Generalized Anscombe Transformation for Poisson-Gaussian Noise
- Restoration of Poissonian Images Using Alternating Direction Optimization
- Spatially adapted regularization parameter selection based on the local discrepancy function for Poissonian image deblurring
- The Little Engine that Could: Regularization by Denoising (RED)
- THE TRANSFORMATION OF POISSON, BINOMIAL AND NEGATIVE-BINOMIAL DATA
- Constrained and unconstrained deep image prior optimization models with automatic regularization
- A noise-robust online convolutional coding model and its applications to Poisson denoising and image fusion
- Regularized generalized inverse accelerating linearized alternating minimization algorithm for frame-based Poissonian image deblurring
- Learning deep optimizer for blind image deconvolution
- Restoring severely out-of-focus blurred text images with deep image prior
- 3D Poissonian image deblurring via patch-based tensor logarithmic Schatten-\(p\) minimization
This page was built for publication: Blind Poissonian image deblurring regularized by a denoiser constraint and deep image prior
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2007170)
