# Stochastic Deep Restoration Priors for Imaging Inverse Problems

arXiv: https://arxiv.org/abs/2410.02057 · HTML: https://mlsanity.com/paper/2410.02057/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Oct 2024.

## Built on by (most cited first, 14 of 14)

- [Proximal Algorithm Unrolling: Flexible and Efficient Reconstruction Networks for Single-Pixel Imaging](https://mlsanity.com/paper/2505.23180/) (2025)
- [FiRe: Fixed-points of Restoration Priors for Solving Inverse Problems](https://mlsanity.com/paper/2411.18970/) (2024)
- [Whitened Score Diffusion: A Structured Prior for Imaging Inverse Problems](https://mlsanity.com/paper/2505.10311/) (2025)
- [Kernel Density Steering: Inference-Time Scaling via Mode Seeking for Image Restoration](https://mlsanity.com/paper/2507.05604/) (2025)
- [Robust multi-coil MRI reconstruction via self-supervised denoising](https://mlsanity.com/paper/2411.12919/) (2024)
- [NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems](https://mlsanity.com/paper/2510.01608/) (2025)
- [Reconstruct Anything Model: a lightweight general model for computational imaging](https://mlsanity.com/paper/2503.08915/) (2025)
- [RSR-NF: Neural Field Regularization by Static Restoration Priors for Dynamic Imaging](https://mlsanity.com/paper/2503.10015/) (2025)
- [Multimodal Diffusion Bridge with Attention-Based SAR Fusion for Satellite Image Cloud Removal](https://mlsanity.com/paper/2504.03607/) (2025)
- [Equivariant Denoisers for Image Restoration](https://mlsanity.com/paper/2412.05343/) (2024)
- [Comprehensive Examination of Unrolled Networks for Solving Linear Inverse Problems](https://mlsanity.com/paper/2501.04608/) (2025)
- [Analysis Plug-and-Play Methods for Imaging Inverse Problems](https://mlsanity.com/paper/2509.15422/) (2025)
- [Generative Manifold Distillation: Aligning Restoration Trajectories with Natural Image Prior](https://mlsanity.com/paper/2512.11121/) (2025)
- [Learning Normalized Energy Models for Linear Inverse Problems](https://mlsanity.com/paper/2605.15487/) (2026)

## Abstract (arXiv)

Deep neural networks trained as image denoisers are widely used as priors for solving imaging inverse problems. While Gaussian denoising is thought sufficient for learning image priors, we show that priors from deep models pre-trained as more general restoration operators can perform better. We introduce Stochastic deep Restoration Priors (ShaRP), a novel method that leverages an ensemble of such restoration models to regularize inverse problems. ShaRP improves upon methods using Gaussian denoiser priors by better handling structured artifacts and enabling self-supervised training even without fully sampled data. We prove ShaRP minimizes an objective function involving a regularizer derived from the score functions of minimum mean square error (MMSE) restoration operators, and theoretically analyze its convergence. Empirically, ShaRP achieves state-of-the-art performance on tasks such as magnetic resonance imaging reconstruction and single-image super-resolution, surpassing both denoiser-and diffusion-model-based methods without requiring retraining.