esrgan

Image upsolver

An enhanced deep learning framework for image super-resolution tasks using Generative Adversarial Networks and PyTorch.

Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution

GitHub

151 stars
6 watching
19 forks
Language: Python
last commit: about 4 years ago
computer-visiondeep-neural-networksgenerative-adversarial-networkimage-processingpytorchsuper-resolution

Related projects:

RepositoryDescriptionStars
brade31919/srgan-tensorflowTensorflow implementation of a generative adversarial network for single image super-resolution848
subeeshvasu/2018_subeesh_epsr_eccvwA deep learning-based super-resolution framework with improved perceptual accuracy and trade-off analysis tools80
trevor-m/tensorflow-srganAn implementation of a generative adversarial network (GAN) used to improve image quality through super-resolution39
cszn/bsrganA deep learning-based approach to super-resolution of degraded images.1,222
warrengreen/srcnnSoftware for enhancing satellite images through deep learning techniques76
jacobgil/pytorch-zssrUnofficial PyTorch implementation of Zero-Shot Super Resolution using Deep Internal Learning from an image alone.201
twtygqyy/pytorch-srresnetAn implementation of a deep learning model for single image super-resolution using a generative adversarial network487
akanimax/pro_gan_pytorchImplementation of a deep learning model for generating high-quality images with improved stability and variation.538
jungmannlab/picassoTools for enhancing image resolution using machine learning algorithms110
wxywhu/srdensenet-pytorchA PyTorch implementation of an image super-resolution model based on dense skip connections.119
uber-research/upsnetDevelops an instance segmentation and panoptic segmentation model for computer vision tasks.648
cszn/srmdDevelops a single convolutional network to handle various image degradations with improved scalability and efficiency427
csailvision/gandissectVisualizes and understands internal representations of generative adversarial networks (GANs) to analyze their behavior and improve performance.1,770
algolzw/dclsA deep learning-based method for image super-resolution using constrained least squares23
cszn/dpsrA deep learning-based method to improve image quality by reducing blur effects839