This repository is a curated collection of resources for super-resolution (SR) research, primarily targeting deep learning practitioners and researchers. It provides a comprehensive overview of state-of-the-art methods, datasets, and evaluation metrics, aiming to accelerate development in the field.

How It Works

The repository categorizes SR techniques into non-deep learning, supervised (generic, face, video, domain-specific), and unsupervised approaches. It meticulously lists papers, often with links to open-access versions, project pages, and code implementations (indicated by asterisks for non-official sources). This structured approach allows users to quickly identify relevant research and explore different methodologies.

Quick Start & Requirements

This repository is a curated list and does not have a direct installation or execution command. It serves as a reference guide to SR research papers and resources.

Highlighted Details

• Comprehensive categorization of SR methods, including non-deep learning, supervised (generic, face, video, domain-specific), and unsupervised techniques.
• Extensive list of SR datasets with details on image counts, pixel counts, formats, and descriptions.
• Compilation of common SR evaluation metrics with links to their respective papers.
• Includes a survey paper ("Deep Learning for Image Super-resolution: A Survey") that analyzes SR models by components and identifies open issues.

Maintenance & Community

The repository is maintained by ptkin and aims to be continuously updated. Suggestions and questions are welcomed. Links to related GitHub repositories and Papers With Code are provided.

Licensing & Compatibility

The repository itself does not specify a license. Individual papers and code linked within may have their own licenses. Compatibility for commercial use or closed-source linking would depend on the licenses of the referenced projects.

Limitations & Caveats

This repository is a curated list of research papers and does not provide executable code or a unified framework. Links to code are often external and may require specific environments or dependencies. Some code links are marked with asterisks, indicating they might not be official or fully maintained.