Awesome Deblurring

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.