[ICCV 2019] "DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better" by Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang Wang

Tensorflow implementation of DeblurGAN(Blind Motion Deblurring Using Conditional Adversarial Networks)

Unofficial tensorflow (tf) implementation of DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks

An easy-to-read implementation of DeblurGAN

This is a lightweight GAN developed for real-time deblurring. The model has a super tiny size and a rapid inference time. The motivation is to boost marker detection in robotic applications, however, you may use it for other applications definitely.

Transfer DeBlurGan to dehaze

Using deblur GAN on custom dataset

This is a very simplified ipynb code for KupynOrest's Deblur GAN code. DeblurGAN addresses the challenge of end-to-end image deblurring through the use of conditional Generative Adversarial Networks (cGANs).I have used pytorch for this implementation.

Implement DeblurGAN with TensorFlow

This repository consists the source code for the image enhancement pipeline built during the second round of Ethos Hackathon at IIT Guwahati. This pipeline integrates SRCNN, LIME and DeblurGAN for the enhancement of low quality CCTV frames. Also integrates VGGface face recognition model.

First Round submission for the Ethos Hackathon. This repository consists of the basic implementation of two model SRCNN and DeblurGANv2.

Image Deblurring using Generative Adversarial Networks