# R3L: Connecting Deep Reinforcement Learning to Recurrent Neural Networks for Image Denoising via Residual Recovery

arXiv: https://arxiv.org/abs/2107.05318 · HTML: https://mlsanity.com/paper/2107.05318/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 26 references that are in the map.
- First posted on arXiv 12 Jul 2021.

## Builds on (most cited first, 14 of 14)

- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Attention, Learn to Solve Routing Problems!](https://mlsanity.com/paper/1803.08475/) (2018)
- [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017)
- [Toward Convolutional Blind Denoising of Real Photographs](https://mlsanity.com/paper/1807.04686/) (2018)
- [Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration](https://mlsanity.com/paper/1508.02848/) (2015)
- [Non-Local Recurrent Network for Image Restoration](https://mlsanity.com/paper/1806.02919/) (2018)
- [Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning](https://mlsanity.com/paper/1804.03312/) (2018)
- [When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach](https://mlsanity.com/paper/1706.04284/) (2017)
- [Path-Restore: Learning Network Path Selection for Image Restoration](https://mlsanity.com/paper/1904.10343/) (2019)
- [Connecting Image Denoising and High-Level Vision Tasks via Deep Learning](https://mlsanity.com/paper/1809.01826/) (2018)
- [Recurrent Inference Machines for Solving Inverse Problems](https://mlsanity.com/paper/1706.04008/) (2017)
- [Fully Convolutional Network with Multi-Step Reinforcement Learning for Image Processing](https://mlsanity.com/paper/1811.04323/) (2018)
- [Mixture of Pre-processing Experts Model for Noise Robust Deep Learning on Resource Constrained Platforms](https://mlsanity.com/paper/1904.12426/) (2019)

## Built on by (most cited first, 4 of 4)

- [ReLLIE: Deep Reinforcement Learning for Customized Low-Light Image Enhancement](https://mlsanity.com/paper/2107.05830/) (2021)
- [REPNP: Plug-and-Play with Deep Reinforcement Learning Prior for Robust Image Restoration](https://mlsanity.com/paper/2207.12056/) (2022)
- [Reinforcement Learning of Self Enhancing Camera Image and Signal Processing](https://mlsanity.com/paper/2111.07499/) (2021)
- [PPORLD-EDNetLDCT: A Proximal Policy Optimization-Based Reinforcement Learning Framework for Adaptive Low-Dose CT Denoising](https://mlsanity.com/paper/2509.03185/) (2025)

## Abstract (arXiv)

State-of-the-art image denoisers exploit various types of deep neural networks via deterministic training. Alternatively, very recent works utilize deep reinforcement learning for restoring images with diverse or unknown corruptions. Though deep reinforcement learning can generate effective policy networks for operator selection or architecture search in image restoration, how it is connected to the classic deterministic training in solving inverse problems remains unclear. In this work, we propose a novel image denoising scheme via Residual Recovery using Reinforcement Learning, dubbed R3L. We show that R3L is equivalent to a deep recurrent neural network that is trained using a stochastic reward, in contrast to many popular denoisers using supervised learning with deterministic losses. To benchmark the effectiveness of reinforcement learning in R3L, we train a recurrent neural network with the same architecture for residual recovery using the deterministic loss, thus to analyze how the two different training strategies affect the denoising performance. With such a unified benchmarking system, we demonstrate that the proposed R3L has better generalizability and robustness in image denoising when the estimated noise level varies, comparing to its counterparts using deterministic training, as well as various state-of-the-art image denoising algorithms.