# Automated Tuning for Diffusion Inverse Problem Solvers without Generative Prior Retraining

arXiv: https://arxiv.org/abs/2509.09880 · HTML: https://mlsanity.com/paper/2509.09880/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 11 Sep 2025.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 23 of 23)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Diffusion Posterior Sampling for General Noisy Inverse Problems](https://mlsanity.com/paper/2209.14687/) (2022)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model](https://mlsanity.com/paper/2212.00490/) (2022)
- [Solving Inverse Problems in Medical Imaging with Score-Based Generative Models](https://mlsanity.com/paper/2111.08005/) (2021)
- [Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing](https://mlsanity.com/paper/1912.10557/) (2019)
- [MoDL: Model Based Deep Learning Architecture for Inverse Problems](https://mlsanity.com/paper/1712.02862/) (2017)
- [Learning a Variational Network for Reconstruction of Accelerated MRI Data](https://mlsanity.com/paper/1704.00447/) (2017)
- [Robust Compressed Sensing MRI with Deep Generative Priors](https://mlsanity.com/paper/2108.01368/) (2021)
- [Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems](https://mlsanity.com/paper/2303.05754/) (2023)
- [Deep Learning Methods for Parallel Magnetic Resonance Image Reconstruction](https://mlsanity.com/paper/1904.01112/) (2019)
- [Zero-Shot Self-Supervised Learning for MRI Reconstruction](https://mlsanity.com/paper/2102.07737/) (2021)
- [Physics-Driven Deep Learning for Computational Magnetic Resonance Imaging](https://mlsanity.com/paper/2203.12215/) (2022)
- [Multi-Mask Self-Supervised Learning for Physics-Guided Neural Networks in Highly Accelerated MRI](https://mlsanity.com/paper/2008.06029/) (2020)
- [Self-Supervised Physics-Guided Deep Learning Reconstruction For High-Resolution 3D LGE CMR](https://mlsanity.com/paper/2011.09414/) (2020)
- [20-fold Accelerated 7T fMRI Using Referenceless Self-Supervised Deep Learning Reconstruction](https://mlsanity.com/paper/2105.05827/) (2021)
- [Zero-Shot Adaptation for Approximate Posterior Sampling of Diffusion Models in Inverse Problems](https://mlsanity.com/paper/2407.11288/) (2024)
- [Sparsity-Driven Parallel Imaging Consistency for Improved Self-Supervised MRI Reconstruction](https://mlsanity.com/paper/2505.24136/) (2025)
- [Diff-Unfolding: A Model-Based Score Learning Framework for Inverse Problems](https://mlsanity.com/paper/2505.11393/) (2025)

## Built on by (most cited first, 2 of 2)

- [PnP-CM: Consistency Models as Plug-and-Play Priors for Inverse Problems](https://mlsanity.com/paper/2509.22736/) (2025)
- [Time-Embedded Algorithm Unrolling for Computational MRI](https://mlsanity.com/paper/2510.16321/) (2025)

## Abstract (arXiv)

Diffusion/score-based models have recently emerged as powerful generative priors for solving inverse problems, including accelerated MRI reconstruction. While their flexibility allows decoupling the measurement model from the learned prior, their performance heavily depends on carefully tuned data fidelity weights, especially under fast sampling schedules with few denoising steps. Existing approaches often rely on heuristics or fixed weights, which fail to generalize across varying measurement conditions and irregular timestep schedules. In this work, we propose Zero-shot Adaptive Diffusion Sampling (ZADS), a test-time optimization method that adaptively tunes fidelity weights across arbitrary noise schedules without requiring retraining of the diffusion prior. ZADS treats the denoising process as a fixed unrolled sampler and optimizes fidelity weights in a self-supervised manner using only undersampled measurements. Experiments on the fastMRI knee dataset demonstrate that ZADS consistently outperforms both traditional compressed sensing and recent diffusion-based methods, showcasing its ability to deliver high-fidelity reconstructions across varying noise schedules and acquisition settings.