A curated list of academic papers, datasets, and resources for image and video deblurring research.
Awesome-Deblurring is a curated, community-maintained list of academic resources focused on image and video deblurring algorithms. It compiles research papers, code implementations, and datasets to help researchers and developers quickly access the state of the art in blur removal techniques. The repository categorizes works by problem type (e.g., blind vs. non-blind deblurring) and methodology, providing a structured overview of the field's evolution.
Computer vision researchers, graduate students, and engineers working on image restoration, computational photography, or video enhancement who need a comprehensive reference for deblurring literature and tools.
It saves significant time in literature review by aggregating and organizing hundreds of relevant papers with direct links to code and data. Unlike generic academic search engines, it is specifically tailored to deblurring, maintained by the community, and includes both classical and deep learning approaches.
A curated list of resources for Image and Video Deblurring
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Curates hundreds of academic papers from top conferences (CVPR, ICCV, ECCV) and journals, spanning foundational works from 2006 to the latest state-of-the-art in 2024-2025, as detailed in the structured tables with year, publication, and links.
Resources are systematically categorized by deblurring type (e.g., single-image blind, non-blind, video) and methodology (non-deep learning vs. deep learning), making it easy to navigate specific subfields without sifting through unrelated literature.
Many entries include direct links to official GitHub repositories and benchmark datasets like GoPro and HIDE, enabling quick access to implementations and evaluation data for reproducibility, as shown in the 'Repo' columns across sections.
Accepts contributions via pull requests, ensuring the repository stays current with emerging research, as emphasized in the project's philosophy of open, organized access to accelerate innovation.
The list merely aggregates papers without providing comparative evaluations, metrics, or rankings, leaving users to assess method effectiveness independently from external sources or original papers.
While code links are given, there's no guidance on setup, dependencies, or integration into real-world applications, making it challenging for non-researchers to deploy these methods without additional effort.
With no curation based on impact or difficulty level, the sheer number of papers—hundreds listed—can be intimidating for those new to the field, requiring additional filtering to identify key works.