# PixelRL: Fully Convolutional Network with Reinforcement Learning for Image Processing

arXiv: https://arxiv.org/abs/1912.07190 · HTML: https://mlsanity.com/paper/1912.07190/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Dec 2019.

## Built on by (most cited first, 13 of 13)

- [Deep reinforcement learning in medical imaging: A literature review](https://mlsanity.com/paper/2103.05115/) (2021)
- [AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection](https://mlsanity.com/paper/2410.22939/) (2024)
- [Reinforcement Learning-powered Semantic Communication via Semantic Similarity](https://mlsanity.com/paper/2108.12121/) (2021)
- [Local Patch AutoAugment with Multi-Agent Collaboration](https://mlsanity.com/paper/2103.11099/) (2021)
- [RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learning](https://mlsanity.com/paper/2212.01737/) (2022)
- [Interactive Medical Image Segmentation with Self-Adaptive Confidence Calibration](https://mlsanity.com/paper/2111.07716/) (2021)
- [RLCorrector: Reinforced Proofreading for Cell-level Microscopy Image Segmentation](https://mlsanity.com/paper/2106.05487/) (2021)
- [A Global Appearance and Local Coding Distortion based Fusion Framework for CNN based Filtering in Video Coding](https://mlsanity.com/paper/2106.12746/) (2021)
- [Closure Discovery for Coarse-Grained Partial Differential Equations Using Grid-based Reinforcement Learning](https://mlsanity.com/paper/2402.00972/) (2024)
- [RL-AWB: Deep Reinforcement Learning for Auto White Balance Correction in Low-Light Night-time Scenes](https://mlsanity.com/paper/2601.05249/) (2026)
- [Reinforcement Learning of Self Enhancing Camera Image and Signal Processing](https://mlsanity.com/paper/2111.07499/) (2021)
- [Efficient Halftoning via Deep Reinforcement Learning](https://mlsanity.com/paper/2304.12152/) (2023)
- [Reinforced Diffusion: Learning to Push the Limits of Anisotropic Diffusion for Image Denoising](https://mlsanity.com/paper/2512.24035/) (2025)

## Abstract (arXiv)

This paper tackles a new problem setting: reinforcement learning with pixel-wise rewards (pixelRL) for image processing. After the introduction of the deep Q-network, deep RL has been achieving great success. However, the applications of deep reinforcement learning (RL) for image processing are still limited. Therefore, we extend deep RL to pixelRL for various image processing applications. In pixelRL, each pixel has an agent, and the agent changes the pixel value by taking an action. We also propose an effective learning method for pixelRL that significantly improves the performance by considering not only the future states of the own pixel but also those of the neighbor pixels. The proposed method can be applied to some image processing tasks that require pixel-wise manipulations, where deep RL has never been applied. Besides, it is possible to visualize what kind of operation is employed for each pixel at each iteration, which would help us understand why and how such an operation is chosen. We also believe that our technology can enhance the explainability and interpretability of the deep neural networks. In addition, because the operations executed at each pixels are visualized, we can change or modify the operations if necessary. We apply the proposed method to a variety of image processing tasks: image denoising, image restoration, local color enhancement, and saliency-driven image editing. Our experimental results demonstrate that the proposed method achieves comparable or better performance, compared with the state-of-the-art methods based on supervised learning. The source code is available on https://github.com/rfuruta/pixelRL.