# Fully Convolutional Network with Multi-Step Reinforcement Learning for Image Processing

arXiv: https://arxiv.org/abs/1811.04323 · HTML: https://mlsanity.com/paper/1811.04323/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Nov 2018.

## Built on by (most cited first, 12 of 12)

- [ReLLIE: Deep Reinforcement Learning for Customized Low-Light Image Enhancement](https://mlsanity.com/paper/2107.05830/) (2021)
- [AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection](https://mlsanity.com/paper/2410.22939/) (2024)
- [Boundary-aware Supervoxel-level Iteratively Refined Interactive 3D Image Segmentation with Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2303.10692/) (2023)
- [R3L: Connecting Deep Reinforcement Learning to Recurrent Neural Networks for Image Denoising via Residual Recovery](https://mlsanity.com/paper/2107.05318/) (2021)
- [Spatial-temporal Hierarchical Reinforcement Learning for Interpretable Pathology Image Super-Resolution](https://mlsanity.com/paper/2406.18310/) (2024)
- [Device-Bind Key-Storageless Hardware AI Model IP Protection: A PUF and Permute-Diffusion Encryption-Enabled Approach](https://mlsanity.com/paper/2212.11133/) (2022)
- [ALL-E: Aesthetics-guided Low-light Image Enhancement](https://mlsanity.com/paper/2304.14610/) (2023)
- [REPNP: Plug-and-Play with Deep Reinforcement Learning Prior for Robust Image Restoration](https://mlsanity.com/paper/2207.12056/) (2022)
- [Image Deraining via Self-supervised Reinforcement Learning](https://mlsanity.com/paper/2403.18270/) (2024)
- [Towards Robust 2D Convolution for Reliable Visual Recognition](https://mlsanity.com/paper/2203.09790/) (2022)
- [RL-CoSeg : A Novel Image Co-Segmentation Algorithm with Deep Reinforcement Learning](https://mlsanity.com/paper/2204.05951/) (2022)
- [Multi-State TD Target for Model-Free Reinforcement Learning](https://mlsanity.com/paper/2405.16522/) (2024)

## 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 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. We apply the proposed method to three image processing tasks: image denoising, image restoration, and local color enhancement. 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.