Learning Gradually Non-convex Image Priors Using Score Matching
- URL: http://arxiv.org/abs/2302.10502v1
- Date: Tue, 21 Feb 2023 08:02:03 GMT
- Title: Learning Gradually Non-convex Image Priors Using Score Matching
- Authors: Erich Kobler and Thomas Pock
- Abstract summary: We propose a unified framework of denoising sufficiently large models in the context of graduated non-ity problems.
These prior learnings can be incorporated into existing algorithms for solving inverse problems.
- Score: 16.10747769038211
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In this paper, we propose a unified framework of denoising score-based models
in the context of graduated non-convex energy minimization. We show that for
sufficiently large noise variance, the associated negative log density -- the
energy -- becomes convex. Consequently, denoising score-based models
essentially follow a graduated non-convexity heuristic. We apply this framework
to learning generalized Fields of Experts image priors that approximate the
joint density of noisy images and their associated variances. These priors can
be easily incorporated into existing optimization algorithms for solving
inverse problems and naturally implement a fast and robust graduated
non-convexity mechanism.
Related papers
- Beyond Image Prior: Embedding Noise Prior into Conditional Denoising Transformer [17.430622649002427]
Existing learning-based denoising methods typically train models to generalize the image prior from large-scale datasets.
We propose a new perspective on the denoising challenge by highlighting the distinct separation between noise and image priors.
We introduce a Locally Noise Prior Estimation algorithm, which accurately estimates the noise prior directly from a single raw noisy image.
arXiv Detail & Related papers (2024-07-12T08:43:11Z) - Gradpaint: Gradient-Guided Inpainting with Diffusion Models [71.47496445507862]
Denoising Diffusion Probabilistic Models (DDPMs) have recently achieved remarkable results in conditional and unconditional image generation.
We present GradPaint, which steers the generation towards a globally coherent image.
We generalizes well to diffusion models trained on various datasets, improving upon current state-of-the-art supervised and unsupervised methods.
arXiv Detail & Related papers (2023-09-18T09:36:24Z) - Score Priors Guided Deep Variational Inference for Unsupervised
Real-World Single Image Denoising [14.486289176696438]
We propose a score priors-guided deep variational inference, namely ScoreDVI, for practical real-world denoising.
We exploit a Non-$i.i.d$ Gaussian mixture model and variational noise posterior to model the real-world noise.
Our method outperforms other single image-based real-world denoising methods and achieves comparable performance to dataset-based unsupervised methods.
arXiv Detail & Related papers (2023-08-09T03:26:58Z) - An Optimization-based Deep Equilibrium Model for Hyperspectral Image
Deconvolution with Convergence Guarantees [71.57324258813675]
We propose a novel methodology for addressing the hyperspectral image deconvolution problem.
A new optimization problem is formulated, leveraging a learnable regularizer in the form of a neural network.
The derived iterative solver is then expressed as a fixed-point calculation problem within the Deep Equilibrium framework.
arXiv Detail & Related papers (2023-06-10T08:25:16Z) - Advancing Unsupervised Low-light Image Enhancement: Noise Estimation, Illumination Interpolation, and Self-Regulation [55.07472635587852]
Low-Light Image Enhancement (LLIE) techniques have made notable advancements in preserving image details and enhancing contrast.
These approaches encounter persistent challenges in efficiently mitigating dynamic noise and accommodating diverse low-light scenarios.
We first propose a method for estimating the noise level in low light images in a quick and accurate way.
We then devise a Learnable Illumination Interpolator (LII) to satisfy general constraints between illumination and input.
arXiv Detail & Related papers (2023-05-17T13:56:48Z) - Representing Noisy Image Without Denoising [91.73819173191076]
Fractional-order Moments in Radon space (FMR) is designed to derive robust representation directly from noisy images.
Unlike earlier integer-order methods, our work is a more generic design taking such classical methods as special cases.
arXiv Detail & Related papers (2023-01-18T10:13:29Z) - Alternating Phase Langevin Sampling with Implicit Denoiser Priors for
Phase Retrieval [1.7767466724342065]
We present a way leveraging the prior implicitly learned by a denoiser to solve phase retrieval problems by incorporating it in a classical framework.
Compared to performant denoising-based algorithms for phase retrieval, we showcase competitive performance with notable measurements on in-distribution images and notable out-of-distribution images.
arXiv Detail & Related papers (2022-11-02T05:08:50Z) - Poisson2Sparse: Self-Supervised Poisson Denoising From a Single Image [34.27748767631027]
We present a novel self-supervised learning method for single-image denoising.
We approximate traditional iterative optimization algorithms for image denoising with a recurrent neural network.
Our method outperforms the state-of-the-art approaches in terms of PSNR and SSIM.
arXiv Detail & Related papers (2022-06-04T00:08:58Z) - Zero-shot Blind Image Denoising via Implicit Neural Representations [77.79032012459243]
We propose an alternative denoising strategy that leverages the architectural inductive bias of implicit neural representations (INRs)
We show that our method outperforms existing zero-shot denoising methods under an extensive set of low-noise or real-noise scenarios.
arXiv Detail & Related papers (2022-04-05T12:46:36Z) - Deep Variational Network Toward Blind Image Restoration [60.45350399661175]
Blind image restoration is a common yet challenging problem in computer vision.
We propose a novel blind image restoration method, aiming to integrate both the advantages of them.
Experiments on two typical blind IR tasks, namely image denoising and super-resolution, demonstrate that the proposed method achieves superior performance over current state-of-the-arts.
arXiv Detail & Related papers (2020-08-25T03:30:53Z) - Solving Linear Inverse Problems Using the Prior Implicit in a Denoiser [7.7288480250888]
We develop a robust and general methodology for making use of implicit priors in deep neural networks.
A CNN trained to perform blind (i.e., with unknown noise level) least-squares denoising is presented.
A generalization of this algorithm to constrained sampling provides a method for using the implicit prior to solve any linear inverse problem.
arXiv Detail & Related papers (2020-07-27T15:40:46Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.