# Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning

arXiv: https://arxiv.org/abs/1907.03029 · HTML: https://mlsanity.com/paper/1907.03029/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jul 2019.

## Built on by (most cited first, 30 of 31)

- [NTIRE 2021 Depth Guided Image Relighting Challenge](https://mlsanity.com/paper/2104.13365/) (2021)
- [Unleashing the Power of Self-Supervised Image Denoising: A Comprehensive Review](https://mlsanity.com/paper/2308.00247/) (2023)
- [Bayesian Image Super-Resolution with Deep Modeling of Image Statistics](https://mlsanity.com/paper/2204.00623/) (2022)
- [Inverting Adversarially Robust Networks for Image Synthesis](https://mlsanity.com/paper/2106.06927/) (2021)
- [Dual Residual Attention Network for Image Denoising](https://mlsanity.com/paper/2305.04269/) (2023)
- [PoGaIN: Poisson-Gaussian Image Noise Modeling from Paired Samples](https://mlsanity.com/paper/2210.04866/) (2022)
- [DiffGAR: Model-Agnostic Restoration from Generative Artifacts Using Image-to-Image Diffusion Models](https://mlsanity.com/paper/2210.08573/) (2022)
- [Listening to the Noise: Blind Denoising with Gibbs Diffusion](https://mlsanity.com/paper/2402.19455/) (2024)
- [Deep Gaussian Denoiser Epistemic Uncertainty and Decoupled Dual-Attention Fusion](https://mlsanity.com/paper/2101.04631/) (2021)
- [Image Blind Denoising Using Dual Convolutional Neural Network with Skip Connection](https://mlsanity.com/paper/2304.01620/) (2023)
- [Fidelity Estimation Improves Noisy-Image Classification With Pretrained Networks](https://mlsanity.com/paper/2106.00673/) (2021)
- [DCANet: Dual Convolutional Neural Network with Attention for Image Blind Denoising](https://mlsanity.com/paper/2304.01498/) (2023)
- [Learning degraded image classification with restoration data fidelity](https://mlsanity.com/paper/2101.09606/) (2021)
- [TRNR: Task-Driven Image Rain and Noise Removal with a Few Images Based on Patch Analysis](https://mlsanity.com/paper/2112.01924/) (2021)
- [Image Denoising with Control over Deep Network Hallucination](https://mlsanity.com/paper/2201.00429/) (2022)
- [LuminanceL1Loss: A loss function which measures percieved brightness and colour differences](https://mlsanity.com/paper/2311.04614/) (2023)
- [Restoring Noisy Demonstration for Imitation Learning With Diffusion Models](https://mlsanity.com/paper/2510.14467/) (2025)
- [Exploring ensembles and uncertainty minimization in denoising networks](https://mlsanity.com/paper/2101.09798/) (2021)
- [Speckles-Training-Based Denoising Convolutional Neural Network Ghost Imaging](https://mlsanity.com/paper/2104.02873/) (2021)
- [Controllable Confidence-Based Image Denoising](https://mlsanity.com/paper/2106.09311/) (2021)
- [Fully Adaptive Bayesian Algorithm for Data Analysis, FABADA](https://mlsanity.com/paper/2201.05145/) (2022)
- [Using Autoencoders on Differentially Private Federated Learning GANs](https://mlsanity.com/paper/2206.12270/) (2022)
- [DSR: Towards Drone Image Super-Resolution](https://mlsanity.com/paper/2208.12327/) (2022)
- [Towards Robust Drone Vision in the Wild](https://mlsanity.com/paper/2208.12655/) (2022)
- [Target Aware Poisson-Gaussian Noise Parameters Estimation from Noisy Images](https://mlsanity.com/paper/2210.12142/) (2022)
- [Fuzzy-Conditioned Diffusion and Diffusion Projection Attention Applied to Facial Image Correction](https://mlsanity.com/paper/2306.14891/) (2023)
- [Two-stage Progressive Residual Dense Attention Network for Image Denoising](https://mlsanity.com/paper/2401.02831/) (2024)
- [prNet: Data-Driven Phase Retrieval via Stochastic Refinement](https://mlsanity.com/paper/2507.09608/) (2025)
- [Coresets for Clustering Under Stochastic Noise](https://mlsanity.com/paper/2510.23438/) (2025)
- [Reading in the Dark: Low-light Scene Text Recognition](https://mlsanity.com/paper/2604.23685/) (2026)

## Abstract (arXiv)

Blind and universal image denoising consists of using a unique model that denoises images with any level of noise. It is especially practical as noise levels do not need to be known when the model is developed or at test time. We propose a theoretically-grounded blind and universal deep learning image denoiser for additive Gaussian noise removal. Our network is based on an optimal denoising solution, which we call fusion denoising. It is derived theoretically with a Gaussian image prior assumption. Synthetic experiments show our network's generalization strength to unseen additive noise levels. We also adapt the fusion denoising network architecture for image denoising on real images. Our approach improves real-world grayscale additive image denoising PSNR results for training noise levels and further on noise levels not seen during training. It also improves state-of-the-art color image denoising performance on every single noise level, by an average of 0.1dB, whether trained on or not.