DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks
Preprint
Abstract
We present DeblurGAN, an end-to-end learned method for motion deblurring. The learning is based on a conditional GAN and the content loss . DeblurGAN achieves state-of-the art performance both in the structural similarity measure and visual appearance. The quality of the deblurring model is also evaluated in a novel way on a real-world problem -- object detection on (de-)blurred images. The method is 5 times faster than the closest competitor -- DeepDeblur. We also introduce a novel method for generating synthetic motion blurred images from sharp ones, allowing realistic dataset augmentation. The model, code and the dataset are available at https://github.com/KupynOrest/DeblurGANKeywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Motion Deblurring in the Wild2017
- Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network2017
- From Motion Blur to Motion Flow: A Deep Learning Solution for Removing Heterogeneous Motion Blur2017
- Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks2017
- Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks2016
- Deep Residual Learning for Image Recognition2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Learning a convolutional neural network for non-uniform motion blur removal2015
- Unnatural L0 Sparse Representation for Natural Image Deblurring2013