mseitzer / Csmri Refinement
Licence: apache-2.0
Code for "Adversarial and Perceptual Refinement Compressed Sensing MRI Reconstruction"
Stars: ✭ 21
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Csmri Refinement
Segan
Speech Enhancement Generative Adversarial Network in TensorFlow
Stars: ✭ 661 (+3047.62%)
Mutual labels: gan, generative-adversarial-networks
Pose2pose
This is a pix2pix demo that learns from pose and translates this into a human. A webcam-enabled application is also provided that translates your pose to the trained pose. Everybody dance now !
Stars: ✭ 182 (+766.67%)
Mutual labels: gan, generative-adversarial-networks
Psgan
Periodic Spatial Generative Adversarial Networks
Stars: ✭ 108 (+414.29%)
Mutual labels: gan, generative-adversarial-networks
Pytorch Pix2pix
Pytorch implementation of pix2pix for various datasets.
Stars: ✭ 74 (+252.38%)
Mutual labels: gan, generative-adversarial-networks
Tensorflow Generative Model Collections
Collection of generative models in Tensorflow
Stars: ✭ 3,785 (+17923.81%)
Mutual labels: gan, generative-adversarial-networks
Dped
Software and pre-trained models for automatic photo quality enhancement using Deep Convolutional Networks
Stars: ✭ 1,315 (+6161.9%)
Mutual labels: gan, generative-adversarial-networks
Generative adversarial networks 101
Keras implementations of Generative Adversarial Networks. GANs, DCGAN, CGAN, CCGAN, WGAN and LSGAN models with MNIST and CIFAR-10 datasets.
Stars: ✭ 138 (+557.14%)
Mutual labels: gan, generative-adversarial-networks
Gdwct
Official PyTorch implementation of GDWCT (CVPR 2019, oral)
Stars: ✭ 122 (+480.95%)
Mutual labels: gan, generative-adversarial-networks
MNIST-invert-color
Invert the color of MNIST images with PyTorch
Stars: ✭ 13 (-38.1%)
Mutual labels: gan, generative-adversarial-networks
mSRGAN-A-GAN-for-single-image-super-resolution-on-high-content-screening-microscopy-images.
Generative Adversarial Network for single image super-resolution in high content screening microscopy images
Stars: ✭ 52 (+147.62%)
Mutual labels: gan, generative-adversarial-networks
Geneva
Code to train and evaluate the GeNeVA-GAN model for the GeNeVA task proposed in our ICCV 2019 paper "Tell, Draw, and Repeat: Generating and modifying images based on continual linguistic instruction"
Stars: ✭ 71 (+238.1%)
Mutual labels: gan, generative-adversarial-networks
Mimicry
[CVPR 2020 Workshop] A PyTorch GAN library that reproduces research results for popular GANs.
Stars: ✭ 458 (+2080.95%)
Mutual labels: gan, generative-adversarial-networks
Keras Gan
Keras implementations of Generative Adversarial Networks.
Stars: ✭ 8,494 (+40347.62%)
Mutual labels: gan, generative-adversarial-networks
Tbgan
Project Page of 'Synthesizing Coupled 3D Face Modalities by Trunk-Branch Generative Adversarial Networks'
Stars: ✭ 105 (+400%)
Mutual labels: gan, generative-adversarial-networks
Cyclegan
PyTorch implementation of CycleGAN
Stars: ✭ 38 (+80.95%)
Mutual labels: gan, generative-adversarial-networks
GAN-Project-2018
GAN in Tensorflow to be run via Linux command line
Stars: ✭ 21 (+0%)
Mutual labels: gan, generative-adversarial-networks
Enlightengan
[IEEE TIP'2021] "EnlightenGAN: Deep Light Enhancement without Paired Supervision" by Yifan Jiang, Xinyu Gong, Ding Liu, Yu Cheng, Chen Fang, Xiaohui Shen, Jianchao Yang, Pan Zhou, Zhangyang Wang
Stars: ✭ 434 (+1966.67%)
Mutual labels: gan, generative-adversarial-networks
Deblur Gan
Keras implementation of "DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks"
Stars: ✭ 483 (+2200%)
Mutual labels: gan, generative-adversarial-networks
Machine Learning
머신러닝 입문자 혹은 스터디를 준비하시는 분들에게 도움이 되고자 만든 repository입니다. (This repository is intented for helping whom are interested in machine learning study)
Stars: ✭ 705 (+3257.14%)
Mutual labels: gan
Code for "Adversarial and Perceptual Refinement Compressed Sensing MRI Reconstruction"
This is the code release for the MICCAI 2018 paper Adversarial and Perceptual Refinement Compressed Sensing MRI Reconstruction by Maximilian Seitzer, Guang Yang, Jo Schlemper, Ozan Oktay, Tobias Würfl, Vincent Christlein, Tom Wong, Raad Mohiaddin, David Firmin, Jennifer Keegan, Daniel Rueckert and Andreas Maier. You can find the paper on arXiv: https://arxiv.org/abs/1806.11216. In this work, we propose a way of training CNNs for MRI reconstruction that enhances perceptual quality of reconstructions while retaining higher PSNR than competing methods.
As the dataset used in the paper is proprietary (we can unfortunately not release it), the code can ultimately serve only illustrative purposes.
However, if you implement a loader for your own MRI dataset, you should be able to run the code with it.
To this end, data/reconstruction/scar_segmentation/scar_segmentation.py may serve as a template for the loader's implementation.
In configs/, three configuration files specifying the exact training parameters we used in the paper are given:
-
1-recnet.json, for training the baseline reconstruction network using just MSE loss -
2-refinement.json, for training the refinement network using adversarial and perceptual losses -
3-train-segmentation-unet.json, for training the segmentation U-Net used to evaluate the semantic interpretability score
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].