# Invertible Denoising Network: A Light Solution for Real Noise Removal

arXiv: https://arxiv.org/abs/2104.10546 · HTML: https://mlsanity.com/paper/2104.10546/

## Key facts

- Cited by 68 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 56 references that are in the map.
- First posted on arXiv 21 Apr 2021.

## Builds on (most cited first, 29 of 29)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [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)
- [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017)
- [Invertible Residual Networks](https://mlsanity.com/paper/1811.00995/) (2018)
- [Learning Enriched Features for Real Image Restoration and Enhancement](https://mlsanity.com/paper/2003.06792/) (2020)
- [Toward Convolutional Blind Denoising of Real Photographs](https://mlsanity.com/paper/1807.04686/) (2018)
- [Unprocessing Images for Learned Raw Denoising](https://mlsanity.com/paper/1811.11127/) (2018)
- [The Reversible Residual Network: Backpropagation Without Storing Activations](https://mlsanity.com/paper/1707.04585/) (2017)
- [Benchmarking Denoising Algorithms with Real Photographs](https://mlsanity.com/paper/1707.01313/) (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)
- [i-RevNet: Deep Invertible Networks](https://mlsanity.com/paper/1802.07088/) (2018)
- [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)
- [Dual Adversarial Network: Toward Real-world Noise Removal and Noise Generation](https://mlsanity.com/paper/2007.05946/) (2020)
- [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)
- [A Trilateral Weighted Sparse Coding Scheme for Real-World Image Denoising](https://mlsanity.com/paper/1807.04364/) (2018)
- [GRDN:Grouped Residual Dense Network for Real Image Denoising and GAN-based Real-world Noise Modeling](https://mlsanity.com/paper/1905.11172/) (2019)
- [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)
- [Identity Enhanced Residual Image Denoising](https://mlsanity.com/paper/2004.13523/) (2020)
- [Pyramid Real Image Denoising Network](https://mlsanity.com/paper/1908.00273/) (2019)

## Built on by (most cited first, 30 of 68)

- [Low-Light Image Enhancement with Normalizing Flow](https://mlsanity.com/paper/2109.05923/) (2021)
- [Image Denoising: The Deep Learning Revolution and Beyond -- A Survey Paper --](https://mlsanity.com/paper/2301.03362/) (2023)
- [Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanisms](https://mlsanity.com/paper/2212.12678/) (2022)
- [Instance Segmentation in the Dark](https://mlsanity.com/paper/2304.14298/) (2023)
- [SepMark: Deep Separable Watermarking for Unified Source Tracing and Deepfake Detection](https://mlsanity.com/paper/2305.06321/) (2023)
- [Reversible Vision Transformers](https://mlsanity.com/paper/2302.04869/) (2023)
- [Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches](https://mlsanity.com/paper/2308.06776/) (2023)
- [Adaptive Dynamic Filtering Network for Image Denoising](https://mlsanity.com/paper/2211.12051/) (2022)
- [Diffusion Model for Generative Image Denoising](https://mlsanity.com/paper/2302.02398/) (2023)
- [Learning Bounds for Open-Set Learning](https://mlsanity.com/paper/2106.15792/) (2021)
- [Variational Deep Image Restoration](https://mlsanity.com/paper/2207.01074/) (2022)
- [Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/2105.01563/) (2021)
- [Large-capacity and Flexible Video Steganography via Invertible Neural Network](https://mlsanity.com/paper/2304.12300/) (2023)
- [Re^2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization](https://mlsanity.com/paper/2211.14053/) (2022)
- [Perceptual Image Enhancement for Smartphone Real-Time Applications](https://mlsanity.com/paper/2210.13552/) (2022)
- [Exploring Efficient Asymmetric Blind-Spots for Self-Supervised Denoising in Real-World Scenarios](https://mlsanity.com/paper/2303.16783/) (2023)
- [CharFormer: A Glyph Fusion based Attentive Framework for High-precision Character Image Denoising](https://mlsanity.com/paper/2207.07798/) (2022)
- [Invertible Rescaling Network and Its Extensions](https://mlsanity.com/paper/2210.04188/) (2022)
- [D2HNet: Joint Denoising and Deblurring with Hierarchical Network for Robust Night Image Restoration](https://mlsanity.com/paper/2207.03294/) (2022)
- [RCRN: Real-world Character Image Restoration Network via Skeleton Extraction](https://mlsanity.com/paper/2207.07795/) (2022)
- [Imperceptible Adversarial Attack via Invertible Neural Networks](https://mlsanity.com/paper/2211.15030/) (2022)
- [Invertible Diffusion Models for Compressed Sensing](https://mlsanity.com/paper/2403.17006/) (2024)
- [Time-Aware Auto White Balance in Mobile Photography](https://mlsanity.com/paper/2504.05623/) (2025)
- [Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image Denoising](https://mlsanity.com/paper/2404.07846/) (2024)
- [Neural Lens Modeling](https://mlsanity.com/paper/2304.04848/) (2023)
- [A Comparison of Image Denoising Methods](https://mlsanity.com/paper/2304.08990/) (2023)
- [Learning Many-to-Many Mapping for Unpaired Real-World Image Super-resolution and Downscaling](https://mlsanity.com/paper/2310.04964/) (2023)
- [A Compact Neural Network-based Algorithm for Robust Image Watermarking](https://mlsanity.com/paper/2112.13491/) (2021)
- [Improving Question Answering over Knowledge Graphs Using Graph Summarization](https://mlsanity.com/paper/2203.13570/) (2022)
- [Optimizing Image Compression via Joint Learning with Denoising](https://mlsanity.com/paper/2207.10869/) (2022)

## Abstract (arXiv)

Invertible networks have various benefits for image denoising since they are lightweight, information-lossless, and memory-saving during back-propagation. However, applying invertible models to remove noise is challenging because the input is noisy, and the reversed output is clean, following two different distributions. We propose an invertible denoising network, InvDN, to address this challenge. InvDN transforms the noisy input into a low-resolution clean image and a latent representation containing noise. To discard noise and restore the clean image, InvDN replaces the noisy latent representation with another one sampled from a prior distribution during reversion. The denoising performance of InvDN is better than all the existing competitive models, achieving a new state-of-the-art result for the SIDD dataset while enjoying less run time. Moreover, the size of InvDN is far smaller, only having 4.2% of the number of parameters compared to the most recently proposed DANet. Further, via manipulating the noisy latent representation, InvDN is also able to generate noise more similar to the original one. Our code is available at: https://github.com/Yang-Liu1082/InvDN.git.