Image denoising via multiscale nonlinear diffusion models
From MaRDI portal
Gaussian denoisingimage denoisingmultiscale pyramid image representationPoisson denoisingtrainable nonlinear reaction diffusion model
Multiple scale methods for ordinary differential equations (34E13) Reaction-diffusion equations (35K57) Variational inequalities (49J40) Inverse problems in optimal control (49N45) Learning and adaptive systems in artificial intelligence (68T05) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)
Abstract: Image denoising is a fundamental operation in image processing and holds considerable practical importance for various real-world applications. Arguably several thousands of papers are dedicated to image denoising. In the past decade, sate-of-the-art denoising algorithm have been clearly dominated by non-local patch-based methods, which explicitly exploit patch self-similarity within image. However, in recent two years, discriminatively trained local approaches have started to outperform previous non-local models and have been attracting increasing attentions due to the additional advantage of computational efficiency. Successful approaches include cascade of shrinkage fields (CSF) and trainable nonlinear reaction diffusion (TNRD). These two methods are built on filter response of linear filters of small size using feed forward architectures. Due to the locality inherent in local approaches, the CSF and TNRD model become less effective when noise level is high and consequently introduces some noise artifacts. In order to overcome this problem, in this paper we introduce a multi-scale strategy. To be specific, we build on our newly-developed TNRD model, adopting the multi-scale pyramid image representation to devise a multi-scale nonlinear diffusion process. As expected, all the parameters in the proposed multi-scale diffusion model, including the filters and the influence functions across scales, are learned from training data through a loss based approach. Numerical results on Gaussian and Poisson denoising substantiate that the exploited multi-scale strategy can successfully boost the performance of the original TNRD model with single scale. As a consequence, the resulting multi-scale diffusion models can significantly suppress the typical incorrect features for those noisy images with heavy noise.
Recommendations
- Speckle reduction with trained nonlinear diffusion filtering
- Image denoising via asymptotic nonlocal filtering
- A general non-local denoising model using multi-kernel-induced measures
- Multi-scale non-standard fourth-order PDE in image denoising and its fixed point algorithm
- Poisson Noise Reduction with Higher-Order Natural Image Prior Model
Cites work
- Adaptive wavelet thresholding for image denoising and compression
- Bayesian Inference on Multiscale Models for Poisson Intensity Estimation: Applications to Photon-Limited Image Denoising
- Fields of experts
- Global Image Denoising
- Image Denoising by Exploring External and Internal Correlations
- Image denoising using scale mixtures of gaussians in the wavelet domain
- Insights Into Analysis Operator Learning: From Patch-Based Sparse Models to Higher Order MRFs
- Introductory lectures on convex optimization. A basic course.
- Is Denoising Dead?
- MsLRR: A Unified Multiscale Low-Rank Representation for Image Segmentation
- Multi-Scale Patch-Based Image Restoration
- Multiscale Image Blind Denoising
- Nonlinear total variation based noise removal algorithms
- On the limited memory BFGS method for large scale optimization
- Optimal Inversion of the Anscombe Transformation in Low-Count Poisson Image Denoising
- Poisson noise reduction with non-local PCA
- Progressive Image Denoising Through Hybrid Graph Laplacian Regularization: A Unified Framework
- Single Image Defogging by Multiscale Depth Fusion
- Sparsity-Based Poisson Denoising With Dictionary Learning
- Why least squares and maximum entropy? An axiomatic approach to inference for linear inverse problems
Cited in
(17)- Image denoising and segmentation via nonlinear diffusion
- Speckle reduction with trained nonlinear diffusion filtering
- Image denoising using generalized anisotropic diffusion
- Fractional derivative based nonlinear diffusion model for image denoising
- Designing rotationally invariant neural networks from PDEs and variational methods
- Diffusion generated methods for denoising target-valued images
- On a cross-diffusion system arising in image denoising
- A general non-local denoising model using multi-kernel-induced measures
- Combination of anisotropic diffusion and non-subsampled shearlet transform for image denoising
- A Class of Multi-scale Models for Image Denoising in Negative Hilbert-Sobolev Spaces
- Conservative scale recomposition for multiscale denoising (the devil is in the high frequency detail)
- scientific article; zbMATH DE number 5077546 (Why is no real title available?)
- Nonlocal adaptive image denoising model
- Denoising using linear and nonlinear multiresolutions II: cell‐average framework and color images
- scientific article; zbMATH DE number 5052074 (Why is no real title available?)
- StressD: 2D stress estimation using denoising diffusion model
- An improved image denoising model based on the directed diffusion equation
This page was built for publication: Image denoising via multiscale nonlinear diffusion models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3130745)
