Convergence Properties of Score-Based Models using Graduated Optimisation for Linear Inverse Problems
- URL: http://arxiv.org/abs/2404.18699v1
- Date: Mon, 29 Apr 2024 13:47:59 GMT
- Title: Convergence Properties of Score-Based Models using Graduated Optimisation for Linear Inverse Problems
- Authors: Pascal Fernsel, Ċ½eljko Kereta, Alexander Denker,
- Abstract summary: We show that score-based generative models (SGMs) can be used to solve inverse problems.
Experiments highlight the potential of using SGs in graduated reconstruction frameworks.
- Score: 44.99833362998488
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The incorporation of generative models as regularisers within variational formulations for inverse problems has proven effective across numerous image reconstruction tasks. However, the resulting optimisation problem is often non-convex and challenging to solve. In this work, we show that score-based generative models (SGMs) can be used in a graduated optimisation framework to solve inverse problems. We show that the resulting graduated non-convexity flow converge to stationary points of the original problem and provide a numerical convergence analysis of a 2D toy example. We further provide experiments on computed tomography image reconstruction, where we show that this framework is able to recover high-quality images, independent of the initial value. The experiments highlight the potential of using SGMs in graduated optimisation frameworks.
Related papers
- Deep Equilibrium Diffusion Restoration with Parallel Sampling [120.15039525209106]
Diffusion model-based image restoration (IR) aims to use diffusion models to recover high-quality (HQ) images from degraded images, achieving promising performance.
Most existing methods need long serial sampling chains to restore HQ images step-by-step, resulting in expensive sampling time and high computation costs.
In this work, we aim to rethink the diffusion model-based IR models through a different perspective, i.e., a deep equilibrium (DEQ) fixed point system, called DeqIR.
arXiv Detail & Related papers (2023-11-20T08:27:56Z) - Convex Latent-Optimized Adversarial Regularizers for Imaging Inverse
Problems [8.33626757808923]
We introduce Convex Latent-d Adrial Regularizers (CLEAR), a novel and interpretable data-driven paradigm.
CLEAR represents a fusion of deep learning (DL) and variational regularization.
Our method consistently outperforms conventional data-driven techniques and traditional regularization approaches.
arXiv Detail & Related papers (2023-09-17T12:06:04Z) - Solving Linear Inverse Problems Provably via Posterior Sampling with
Latent Diffusion Models [98.95988351420334]
We present the first framework to solve linear inverse problems leveraging pre-trained latent diffusion models.
We theoretically analyze our algorithm showing provable sample recovery in a linear model setting.
arXiv Detail & Related papers (2023-07-02T17:21:30Z) - 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) - Equivariance Regularization for Image Reconstruction [5.025654873456756]
We propose a structure-adaptive regularization scheme for solving imaging inverse problems under incomplete measurements.
This regularization scheme utilizes the equivariant structure in the physics of the measurements to mitigate the ill-poseness of the inverse problem.
Our proposed scheme can be applied in a plug-and-play manner alongside with any classic first-order optimization algorithm.
arXiv Detail & Related papers (2022-02-10T14:38:08Z) - Regularization via deep generative models: an analysis point of view [8.818465117061205]
This paper proposes a new way of regularizing an inverse problem in imaging (e.g., deblurring or inpainting) by means of a deep generative neural network.
In many cases our technique achieves a clear improvement of the performance and seems to be more robust.
arXiv Detail & Related papers (2021-01-21T15:04:57Z) - Learned convex regularizers for inverse problems [3.294199808987679]
We propose to learn a data-adaptive input- neural network (ICNN) as a regularizer for inverse problems.
We prove the existence of a sub-gradient-based algorithm that leads to a monotonically decreasing error in the parameter space with iterations.
We show that the proposed convex regularizer is at least competitive with and sometimes superior to state-of-the-art data-driven techniques for inverse problems.
arXiv Detail & Related papers (2020-08-06T18:58:35Z) - 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) - Total Deep Variation for Linear Inverse Problems [71.90933869570914]
We propose a novel learnable general-purpose regularizer exploiting recent architectural design patterns from deep learning.
We show state-of-the-art performance for classical image restoration and medical image reconstruction problems.
arXiv Detail & Related papers (2020-01-14T19:01:50Z)
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.