# Bayesian Image Reconstruction using Deep Generative Models

arXiv: https://arxiv.org/abs/2012.04567 · HTML: https://mlsanity.com/paper/2012.04567/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Dec 2020.

## Built on by (most cited first, 29 of 29)

- [Score-based diffusion models for accelerated MRI](https://mlsanity.com/paper/2110.05243/) (2021)
- [ResDiff: Combining CNN and Diffusion Model for Image Super-Resolution](https://mlsanity.com/paper/2303.08714/) (2023)
- [InverseSR: 3D Brain MRI Super-Resolution Using a Latent Diffusion Model](https://mlsanity.com/paper/2308.12465/) (2023)
- [BIPS: Bi-modal Indoor Panorama Synthesis via Residual Depth-aided Adversarial Learning](https://mlsanity.com/paper/2112.06179/) (2021)
- [Bayesian Imaging With Data-Driven Priors Encoded by Neural Networks: Theory, Methods, and Algorithms](https://mlsanity.com/paper/2103.10182/) (2021)
- [Semantic uncertainty intervals for disentangled latent spaces](https://mlsanity.com/paper/2207.10074/) (2022)
- [Prior Image-Constrained Reconstruction using Style-Based Generative Models](https://mlsanity.com/paper/2102.12525/) (2021)
- [Robust Unsupervised StyleGAN Image Restoration](https://mlsanity.com/paper/2302.06733/) (2023)
- [Conditional Injective Flows for Bayesian Imaging](https://mlsanity.com/paper/2204.07664/) (2022)
- [Universal Functional Regression with Neural Operator Flows](https://mlsanity.com/paper/2404.02986/) (2024)
- [Traversing Distortion-Perception Tradeoff using a Single Score-Based Generative Model](https://mlsanity.com/paper/2503.20297/) (2025)
- [CAFLOW: Conditional Autoregressive Flows](https://mlsanity.com/paper/2106.02531/) (2021)
- [Report on the AAPM Grand Challenge on deep generative modeling for learning medical image statistics](https://mlsanity.com/paper/2405.01822/) (2024)
- [Differentiable Gaussianization Layers for Inverse Problems Regularized by Deep Generative Models](https://mlsanity.com/paper/2112.03860/) (2021)
- [FusionVAE: A Deep Hierarchical Variational Autoencoder for RGB Image Fusion](https://mlsanity.com/paper/2209.11277/) (2022)
- [Safety Monitoring of Machine Learning Perception Functions: a Survey](https://mlsanity.com/paper/2412.06869/) (2024)
- [StyleGAN-induced data-driven regularization for inverse problems](https://mlsanity.com/paper/2110.03814/) (2021)
- [X2CT-FLOW: Maximum a posteriori reconstruction using a progressive flow-based deep generative model for ultra sparse-view computed tomography in ultra low-dose protocols](https://mlsanity.com/paper/2104.04179/) (2021)
- [Robustness and Exploration of Variational and Machine Learning Approaches to Inverse Problems: An Overview](https://mlsanity.com/paper/2402.12072/) (2024)
- [Deep priors for satellite image restoration with accurate uncertainties](https://mlsanity.com/paper/2412.04130/) (2024)
- [BUFF: Bayesian Uncertainty Guided Diffusion Probabilistic Model for Single Image Super-Resolution](https://mlsanity.com/paper/2504.03490/) (2025)
- [Moir'eXNet: Adaptive Multi-Scale Demoir'eing with Linear Attention Test-Time Training and Truncated Flow Matching Prior](https://mlsanity.com/paper/2506.15929/) (2025)
- [Image Inpainting using Partial Convolution](https://mlsanity.com/paper/2108.08791/) (2021)
- [Diverse super-resolution with pretrained deep hiererarchical VAEs](https://mlsanity.com/paper/2205.10347/) (2022)
- [Super-Resolution through StyleGAN Regularized Latent Search: A Realism-Fidelity Trade-off](https://mlsanity.com/paper/2311.16923/) (2023)
- [Reconstructing Interpretable Features in Computational Super-Resolution microscopy via Regularized Latent Search](https://mlsanity.com/paper/2405.19112/) (2024)
- [MFSR: Multi-fractal Feature for Super-resolution Reconstruction with Fine Details Recovery](https://mlsanity.com/paper/2502.19797/) (2025)
- [COT-AD: Cotton Analysis Dataset](https://mlsanity.com/paper/2507.18532/) (2025)
- [Briding Diffusion Posterior Sampling and Monte Carlo methods: a survey](https://mlsanity.com/paper/2510.14114/) (2025)

## Abstract (arXiv)

Machine learning models are commonly trained end-to-end and in a supervised setting, using paired (input, output) data. Examples include recent super-resolution methods that train on pairs of (low-resolution, high-resolution) images. However, these end-to-end approaches require re-training every time there is a distribution shift in the inputs (e.g., night images vs daylight) or relevant latent variables (e.g., camera blur or hand motion). In this work, we leverage state-of-the-art (SOTA) generative models (here StyleGAN2) for building powerful image priors, which enable application of Bayes' theorem for many downstream reconstruction tasks. Our method, Bayesian Reconstruction through Generative Models (BRGM), uses a single pre-trained generator model to solve different image restoration tasks, i.e., super-resolution and in-painting, by combining it with different forward corruption models. We keep the weights of the generator model fixed, and reconstruct the image by estimating the Bayesian maximum a-posteriori (MAP) estimate over the input latent vector that generated the reconstructed image. We further use variational inference to approximate the posterior distribution over the latent vectors, from which we sample multiple solutions. We demonstrate BRGM on three large and diverse datasets: (i) 60,000 images from the Flick Faces High Quality dataset (ii) 240,000 chest X-rays from MIMIC III and (iii) a combined collection of 5 brain MRI datasets with 7,329 scans. Across all three datasets and without any dataset-specific hyperparameter tuning, our simple approach yields performance competitive with current task-specific state-of-the-art methods on super-resolution and in-painting, while being more generalisable and without requiring any training. Our source code and pre-trained models are available online: https://razvanmarinescu.github.io/brgm/.