# Disentangling Noise from Images: A Flow-Based Image Denoising Neural Network

arXiv: https://arxiv.org/abs/2105.04746 · HTML: https://mlsanity.com/paper/2105.04746/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 44 references that are in the map.
- First posted on arXiv 11 May 2021.

## Builds on (most cited first, 25 of 25)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [Image Segmentation Using Deep Learning: A Survey](https://mlsanity.com/paper/2001.05566/) (2020)
- [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017)
- [Learning Deep CNN Denoiser Prior for Image Restoration](https://mlsanity.com/paper/1704.03264/) (2017)
- [Toward Convolutional Blind Denoising of Real Photographs](https://mlsanity.com/paper/1807.04686/) (2018)
- [MemNet: A Persistent Memory Network for Image Restoration](https://mlsanity.com/paper/1708.02209/) (2017)
- [Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration](https://mlsanity.com/paper/1508.02848/) (2015)
- [Real Image Denoising with Feature Attention](https://mlsanity.com/paper/1904.07396/) (2019)
- [Guided Image Generation with Conditional Invertible Neural Networks](https://mlsanity.com/paper/1907.02392/) (2019)
- [Variational Denoising Network: Toward Blind Noise Modeling and Removal](https://mlsanity.com/paper/1908.11314/) (2019)
- [Noise Flow: Noise Modeling with Conditional Normalizing Flows](https://mlsanity.com/paper/1908.08453/) (2019)
- [Transfer Learning from Synthetic to Real-Noise Denoising with Adaptive Instance Normalization](https://mlsanity.com/paper/2002.11244/) (2020)
- [Invertible Image Rescaling](https://mlsanity.com/paper/2005.05650/) (2020)
- [Real-world Noisy Image Denoising: A New Benchmark](https://mlsanity.com/paper/1804.02603/) (2018)
- [A Remote Sensing Image Dataset for Cloud Removal](https://mlsanity.com/paper/1901.00600/) (2019)
- [Class-Aware Fully-Convolutional Gaussian and Poisson Denoising](https://mlsanity.com/paper/1808.06562/) (2018)
- [Are Deep Neural Architectures Losing Information? Invertibility Is Indispensable](https://mlsanity.com/paper/2009.03173/) (2020)
- [Blind Image Denoising via Dependent Dirichlet Process Tree](https://mlsanity.com/paper/1601.03117/) (2016)

## Built on by (most cited first, 7 of 7)

- [Unpaired Deep Image Dehazing Using Contrastive Disentanglement Learning](https://mlsanity.com/paper/2203.07677/) (2022)
- [PD-Flow: A Point Cloud Denoising Framework with Normalizing Flows](https://mlsanity.com/paper/2203.05940/) (2022)
- [Noise2NoiseFlow: Realistic Camera Noise Modeling without Clean Images](https://mlsanity.com/paper/2206.01103/) (2022)
- [Semantic Scene Completion with Cleaner Self](https://mlsanity.com/paper/2303.09977/) (2023)
- [Hierarchical Disentangled Representation for Invertible Image Denoising and Beyond](https://mlsanity.com/paper/2301.13358/) (2023)
- [HIDFlowNet: A Flow-Based Deep Network for Hyperspectral Image Denoising](https://mlsanity.com/paper/2306.17797/) (2023)
- [YeTI: You Only Need Two Noisy Images for Real-World sRGB Noise Generation](https://mlsanity.com/paper/2607.09193/) (2026)

## Abstract (arXiv)

The prevalent convolutional neural network (CNN) based image denoising methods extract features of images to restore the clean ground truth, achieving high denoising accuracy. However, these methods may ignore the underlying distribution of clean images, inducing distortions or artifacts in denoising results. This paper proposes a new perspective to treat image denoising as a distribution learning and disentangling task. Since the noisy image distribution can be viewed as a joint distribution of clean images and noise, the denoised images can be obtained via manipulating the latent representations to the clean counterpart. This paper also provides a distribution learning based denoising framework. Following this framework, we present an invertible denoising network, FDN, without any assumptions on either clean or noise distributions, as well as a distribution disentanglement method. FDN learns the distribution of noisy images, which is different from the previous CNN based discriminative mapping. Experimental results demonstrate FDN's capacity to remove synthetic additive white Gaussian noise (AWGN) on both category-specific and remote sensing images. Furthermore, the performance of FDN surpasses that of previously published methods in real image denoising with fewer parameters and faster speed. Our code is available at: https://github.com/Yang-Liu1082/FDN.git.