Trustworthy Image Super-Resolution via Generative Pseudoinverse

2025/05/18 by Floros, Andreas, Moosavi-Dezfooli, Seyed-Mohsen, Dragotti, Pier Luigi · 1 citation
#FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2505.12375

Abstract

We consider the problem of trustworthy image restoration, taking the form of a constrained optimization over the prior density. To this end, we develop generative models for the task of image super-resolution that respect the degradation process and that can be made asymptotically consistent with the low-resolution measurements, outperforming existing methods by a large margin in that respect.

Citations

• Looks Too Good To Be True: An Information-Theoretic Analysis of Hallucinations in Generative Restoration Models
• Implicit Diffusion Models for Continuous Super-Resolution
• Invertible Rescaling Network and Its Extensions
• Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling
• Image Super-Resolution via Iterative Refinement
• Improved Denoising Diffusion Probabilistic Models
• Denoising Diffusion Probabilistic Models
• PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models
• A Style-Based Generator Architecture for Generative Adversarial Networks
• Analyzing Inverse Problems with Invertible Neural Networks
• FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Density Estimation Using Real NVP
• Tweedie’s Formula and Selection Bias

Cited by

• On the Anisotropy of Score-Based Generative Models

Related

• Image Super-Resolution with Guarantees via Conformalized Generative Models
• Evaluating and Preserving High-level Fidelity in Super-Resolution
• Perceptual Image Restoration with High-Quality Priori and Degradation Learning
• Image Super-Resolution via Iterative Refinement
• Image Restoration from Parametric Transformations using Generative Models