Equivariant Denoisers for Image Restoration
- URL: http://arxiv.org/abs/2412.05343v1
- Date: Fri, 06 Dec 2024 10:22:00 GMT
- Title: Equivariant Denoisers for Image Restoration
- Authors: Marien Renaud, Arthur Leclaire, Nicolas Papadakis,
- Abstract summary: We propose a unified framework named Equivariant Regularization by Denoising (ERED) based on equivariant denoisers and optimization.
We analyze the convergence of this algorithm and discuss its practical benefit.
- Score: 8.865896660863681
- License:
- Abstract: One key ingredient of image restoration is to define a realistic prior on clean images to complete the missing information in the observation. State-of-the-art restoration methods rely on a neural network to encode this prior. Moreover, typical image distributions are invariant to some set of transformations, such as rotations or flips. However, most deep architectures are not designed to represent an invariant image distribution. Recent works have proposed to overcome this difficulty by including equivariance properties within a Plug-and-Play paradigm. In this work, we propose a unified framework named Equivariant Regularization by Denoising (ERED) based on equivariant denoisers and stochastic optimization. We analyze the convergence of this algorithm and discuss its practical benefit.
Related papers
- Learning of Patch-Based Smooth-Plus-Sparse Models for Image Reconstruction [14.93489065234423]
We formulate the optimization as a bilevel problem.
We evaluate our method for denoising, super-resolution, and compressed-sensing magnetic-resonance imaging.
arXiv Detail & Related papers (2024-12-17T16:34:32Z) - Compositional Inversion for Stable Diffusion Models [64.79261401944994]
Inversion methods generate personalized images by incorporating concepts of interest provided by user images.
Existing methods often suffer from overfitting issues, where the dominant presence of inverted concepts leads to the absence of other desired concepts.
We propose a method that guides the inversion process towards the core distribution for compositional embeddings.
arXiv Detail & Related papers (2023-12-13T10:57:46Z) - Equivariant plug-and-play image reconstruction [10.781078029828473]
Plug-and-play algorithms can leverage powerful pre-trained denoisers to solve inverse imaging problems.
We show that enforcing equivariance to certain groups of transformations on the denoiser improves the stability of the algorithm as well as its reconstruction quality.
Experiments on multiple imaging modalities and denoising networks show that the equivariant plug-and-play algorithm improves both the reconstruction performance and the stability compared to their non-equivariant counterparts.
arXiv Detail & Related papers (2023-12-04T12:07:39Z) - A Variational Perspective on Solving Inverse Problems with Diffusion
Models [101.831766524264]
Inverse tasks can be formulated as inferring a posterior distribution over data.
This is however challenging in diffusion models since the nonlinear and iterative nature of the diffusion process renders the posterior intractable.
We propose a variational approach that by design seeks to approximate the true posterior distribution.
arXiv Detail & Related papers (2023-05-07T23:00:47Z) - 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) - Imaging with Equivariant Deep Learning [9.333799633608345]
We review the emerging field of equivariant imaging and show how it can provide improved generalization and new imaging opportunities.
We show the interplay between the acquisition physics and group actions and links to iterative reconstruction, blind compressed sensing and self-supervised learning.
arXiv Detail & Related papers (2022-09-05T02:13:57Z) - A training-free recursive multiresolution framework for diffeomorphic
deformable image registration [6.929709872589039]
We propose a novel diffeomorphic training-free approach for deformable image registration.
The proposed architecture is simple in design. The moving image is warped successively at each resolution and finally aligned to the fixed image.
The entire system is end-to-end and optimized for each pair of images from scratch.
arXiv Detail & Related papers (2022-02-01T15:17:17Z) - Denoising Diffusion Restoration Models [110.1244240726802]
Denoising Diffusion Restoration Models (DDRM) is an efficient, unsupervised posterior sampling method.
We demonstrate DDRM's versatility on several image datasets for super-resolution, deblurring, inpainting, and colorization.
arXiv Detail & Related papers (2022-01-27T20:19:07Z) - 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) - A Flexible Framework for Designing Trainable Priors with Adaptive
Smoothing and Game Encoding [57.1077544780653]
We introduce a general framework for designing and training neural network layers whose forward passes can be interpreted as solving non-smooth convex optimization problems.
We focus on convex games, solved by local agents represented by the nodes of a graph and interacting through regularization functions.
This approach is appealing for solving imaging problems, as it allows the use of classical image priors within deep models that are trainable end to end.
arXiv Detail & Related papers (2020-06-26T08:34:54Z)
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.