A Stability Benchmark of Generative Regularizers for Inverse Problems

• URL: http://arxiv.org/abs/2605.10076v1
• Date: Mon, 11 May 2026 06:58:30 GMT
• Title: A Stability Benchmark of Generative Regularizers for Inverse Problems
• Abstract summary: We benchmark generative approaches against modern optimization-based methods inspired by the widely used variational techniques.<n>Our results give insights for which settings and applications generative priors can deliver state-of-the-art reconstructions.
• Score: 48.95664664242498
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative (diffusion) priors demonstrate remarkable performance in addressing inverse problems in imaging. Yet, for scientific and medical imaging, it is crucial that reconstruction techniques remain stable and reliable under imperfect settings. Typical definitions of stability encompass the notion of ''convergent regularization'', robustness to out-of-distribution data, and to inaccuracies in the forward operator or noise model. We evaluate these properties numerically. Furthermore, we benchmark generative approaches against modern optimization-based methods inspired by the widely used variational techniques. Our results give insights for which settings and applications generative priors can deliver state-of-the-art reconstructions, and on those in which they fall short or may even be problematic.

Related papers

• The Road Taken: The Role of Optimizers at the Edge of Stability [53.81268610971847]
  edge of stability refers to a phenomenon in deep learning where the Hessian eigenvalues of the loss remain stable above a threshold that the classical descent predicts to be unstable.<n>Previous works formulate the edge of stability with respect to the maximum Hessian eigenvalue and the learning rate.<n>We observe that many first-order methods, including gradient descent, significantly violate the stability bound predicted by these theories by a factor as large as $times 21.1$.
  arXiv  Detail & Related papers  (2026-08-19T01:03:34Z)
• Unconstrained Multi-view Human Pose Estimation with Algebraic Priors [28.69737225698459]
  We propose an unconstrained framework that synergizes deep neural networks, algebraic priors, and temporal dynamics for uncalibrated pose estimation.<n>Our framework establishes a new state-of-the-art for uncalibrated multi-view human pose estimation.
  arXiv  Detail & Related papers  (2026-04-27T11:01:55Z)
• From sparse recovery to plug-and-play priors, understanding trade-offs for stable recovery with generalized projected gradient descent [2.599882743586164]
  We consider the problem of recovering an unknown low-dimensional vector from noisy, underdetermined observations.<n>We focus on the Generalized Projected Gradient Descent (GPGD) framework, which unifies traditional sparse recovery methods and modern approaches.
  arXiv  Detail & Related papers  (2025-12-08T10:31:48Z)
• Solving Inverse Problems with FLAIR [68.87167940623318]
  We present FLAIR, a training-free variational framework that leverages flow-based generative models as prior for inverse problems.<n>Results on standard imaging benchmarks demonstrate that FLAIR consistently outperforms existing diffusion- and flow-based methods in terms of reconstruction quality and sample diversity.
  arXiv  Detail & Related papers  (2025-06-03T09:29:47Z)
• Rigorous Probabilistic Guarantees for Robust Counterfactual Explanations [80.86128012438834]
  We show for the first time that computing the robustness of counterfactuals with respect to plausible model shifts is NP-complete. We propose a novel probabilistic approach which is able to provide tight estimates of robustness with strong guarantees.
  arXiv  Detail & Related papers  (2024-07-10T09:13:11Z)
• Stability of Data-Dependent Ridge-Regularization for Inverse Problems [0.0]
  We propose learning a pixel-based ridge regularizer with a data-dependent and spatially varying regularization strength.<n>We prove that the reconstruction forms a maximum-a-posteriori approach.
  arXiv  Detail & Related papers  (2024-06-18T05:49:54Z)
• 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)
• DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection [80.20339155618612]
  DiffusionAD is a novel anomaly detection pipeline comprising a reconstruction sub-network and a segmentation sub-network.<n>A rapid one-step denoising paradigm achieves hundreds of times acceleration while preserving comparable reconstruction quality.<n>Considering the diversity in the manifestation of anomalies, we propose a norm-guided paradigm to integrate the benefits of multiple noise scales.
  arXiv  Detail & Related papers  (2023-03-15T16:14:06Z)
• Making Reconstruction-based Method Great Again for Video Anomaly Detection [64.19326819088563]
  Anomaly detection in videos is a significant yet challenging problem. Existing reconstruction-based methods rely on old-fashioned convolutional autoencoders. We propose a new autoencoder model for enhanced consecutive frame reconstruction.
  arXiv  Detail & Related papers  (2023-01-28T01:57:57Z)

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.