Multi-Step Reinforcement Learning for Single Image Super-Resolution

2020-07-28 · IEEE/CVF 2020 7 · Kyle Vassilo, Cory Heatwole, Tarek Taha, Asif Mehmood

Deep Learning (DL) has become prevalent in today's image processing research due to its power and versatility. It has dominated the Single Image Super-Resolution (SISR) field with its ability to obtain High-Resolution (HR) images from their Low-Resolution (LR) counterparts, particularly using Generative Adversarial Networks (GANs). Interest in SISR comes from its potential to increase the performance of supplementary image processing tasks such as object detection, localization, and classification. This research applies a multi-agent Reinforcement Learning (RL) algorithm to SISR, creating an advanced ensemble approach for combining powerful GANs. In our implementation each agent chooses a particular action from a fixed action set comprised of results from existing GAN SISR algorithms to update its pixel values. The pixel-wise or patch-wise arrangement of agents and rewards encourages the algorithm to learn a strategy to increase the resolution of an image by choosing the best pixel values from each option.

📄 PDF Abstract BibTeX

Code (1)

Nhat-Thanh/PixelRL-SR pytorch

Tasks

Image Super-Resolution Multi-agent Reinforcement Learning object-detection Object Detection reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Super-Resolution

RefineSVG: Visual Feedback-Driven Reinforcement Learning for Image-to-SVG Generation

2026-07-30 · Shaobo Liu, Feiqiao Mao, Shuaishuai Zhou, Yan Zhan 외 arxiv

We propose RefineSVG, a single-step closed-loop visual feedback framework that enables multimodal large language models (MLLMs) to perform high-fidelity image-to-SVG generation through self-correction. Existing MLLM-base…

Reinforcement Learning

Exploring the Performance Frontier of Compact Unified Image Generation Models

2026-08-20 · Taihang Hu, Zhao Wang, Zuan Gao, Tao Liu 외 arxiv

We present Swift-Image, a compact unified model for text-to-image generation, single-image editing, and multi-image editing. Our goal is to explore how far a relatively small visual generator can be pushed through system…

Text-to-Image Generation Reinforcement Learning Model Compression Image Editing

Three Steps at a Time: Learning Representations from Action Sequences in Contrastive RL

2026-08-31 · Michal Korniak, Kamil Dybek, Benjamin Eysenbach, Marco Bagatella 외 arxiv

While self-supervised approaches to reinforcement learning have achieved strong results by learning representations of states and actions, a key open question is the time scale over which actions should be modeled. Depar…

Reinforcement Learning

Distilling Reinforcement Learning into Single-Batch Datasets

2025-08-12 · Connor Wilhelm, Dan Ventura arxiv

Dataset distillation compresses a large dataset into a small synthetic dataset such that learning on the synthetic dataset approximates learning on the original. Training on the distilled dataset can be performed in as l…

Reinforcement Learning Atari Games

Deep Reinforcement Learning of Volume-guided Progressive View Inpainting for 3D Point Scene Completion from a Single Depth Image

2019-03-10 · CVPR 2019 6 · Xiaoguang Han, Zhaoxuan Zhang, Dong Du, Mingdai Yang 외

We present a deep reinforcement learning method of progressive view inpainting for 3D point scene completion under volume guidance, achieving high-quality scene reconstruction from only a single depth image with severe o…

Deep Reinforcement Learning Reinforcement Learning