# abdullah-abuolaim/recurrent-defocus-deblurring-synth-dual-pixel

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/abdullah-abuolaim-recurrent-defocus-deblurring-synth-dual-pixel).**

_How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._

55 stars · 8 forks · Python · Apache-2.0

## Links

- GitHub: https://github.com/Abdullah-Abuolaim/recurrent-defocus-deblurring-synth-dual-pixel
- awesome-repositories: https://awesome-repositories.com/repository/abdullah-abuolaim-recurrent-defocus-deblurring-synth-dual-pixel.md

## Description

Reference github repository for the paper "Learning to Reduce Defocus Blur by Realistically Modeling Dual-Pixel Data". We propose a procedure to generate realistic DP data synthetically. Our synthesis approach mimics the optical image formation found on DP sensors and can be applied to virtual scenes rendered with standard computer software. Leveraging these realistic synthetic DP images, we introduce a new recurrent convolutional network (RCN) architecture that can improve defocus deblurring results and is suitable for use with single-frame and multi-frame data captured by DP sensors.

## Tags

### Part of an Awesome List

- [Defocus Deblurring](https://awesome-repositories.com/f/awesome-lists/ai/defocus-deblurring.md) — Modeling dual-pixel data to reduce defocus blur.