DeblurGAN and DeblurGANv2
DeblurGANv2 is a direct successor that improves upon the original DeblurGAN with faster inference and better image restoration quality, making the first version largely obsolete.
About DeblurGAN
KupynOrest/DeblurGAN
Image Deblurring using Generative Adversarial Networks
Implements Conditional Wasserstein GAN with Gradient Penalty combined with VGG-19 perceptual loss for blind motion deblurring in PyTorch. The architecture generalizes to other image-to-image translation tasks (super-resolution, colorization, inpainting, dehazing) and learns residual corrections from paired blurry-sharp image datasets. Pre-trained generator weights are provided for inference on single images.
About DeblurGANv2
VITA-Group/DeblurGANv2
[ICCV 2019] "DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better" by Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang Wang
Employs a Feature Pyramid Network as the core generator component with a relativistic conditional GAN and double-scale discriminator for improved efficiency and quality. The architecture is backbone-agnostic, supporting plug-and-play substitution of feature extractors (Inception-ResNet-v2, MobileNet variants) to balance performance versus speed, enabling real-time video deblurring on lightweight backbones. Built in Python with TensorFlow/Keras, trained on standard benchmarks (GoPro, DVD, NFS) with pretrained models provided for inference via command-line prediction.
Scores updated daily from GitHub, PyPI, and npm data. How scores work