All Projects → zhangqianhui → Exemplar-GAN-Eye-Inpainting-Tensorflow

zhangqianhui / Exemplar-GAN-Eye-Inpainting-Tensorflow

Licence: other
Tensorflow implement of "Eye In-Painting with Exemplar Generative Adversarial Networks"

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Exemplar-GAN-Eye-Inpainting-Tensorflow

Generative inpainting
DeepFill v1/v2 with Contextual Attention and Gated Convolution, CVPR 2018, and ICCV 2019 Oral
Stars: ✭ 2,659 (+2613.27%)
Mutual labels:  generative-adversarial-network, image-inpainting
Edge Connect
EdgeConnect: Structure Guided Image Inpainting using Edge Prediction, ICCV 2019 https://arxiv.org/abs/1901.00212
Stars: ✭ 2,163 (+2107.14%)
Mutual labels:  generative-adversarial-network, image-inpainting
Wasserstein2GenerativeNetworks
PyTorch implementation of "Wasserstein-2 Generative Networks" (ICLR 2021)
Stars: ✭ 38 (-61.22%)
Mutual labels:  generative-adversarial-network
csgan
Task-Aware Compressed Sensing Using Generative Adversarial Networks (published in AAAI18)
Stars: ✭ 25 (-74.49%)
Mutual labels:  generative-adversarial-network
Music-generation-cRNN-GAN
cRNN-GAN to generate music by training on instrumental music (midi)
Stars: ✭ 38 (-61.22%)
Mutual labels:  generative-adversarial-network
Implicit-Internal-Video-Inpainting
[ICCV 2021]: IIVI: Internal Video Inpainting by Implicit Long-range Propagation
Stars: ✭ 190 (+93.88%)
Mutual labels:  image-inpainting
adversarial-recommender-systems-survey
The goal of this survey is two-fold: (i) to present recent advances on adversarial machine learning (AML) for the security of RS (i.e., attacking and defense recommendation models), (ii) to show another successful application of AML in generative adversarial networks (GANs) for generative applications, thanks to their ability for learning (high-…
Stars: ✭ 110 (+12.24%)
Mutual labels:  generative-adversarial-network
deep-learning-roadmap
my own deep learning mastery roadmap
Stars: ✭ 40 (-59.18%)
Mutual labels:  generative-adversarial-network
gan
A 1D toy example of optimizing a generative model using the WGAN-GP model.
Stars: ✭ 21 (-78.57%)
Mutual labels:  generative-adversarial-network
multitask-CycleGAN
Pytorch implementation of multitask CycleGAN with auxiliary classification loss
Stars: ✭ 88 (-10.2%)
Mutual labels:  generative-adversarial-network
WGAN-GP-TensorFlow
TensorFlow implementations of Wasserstein GAN with Gradient Penalty (WGAN-GP), Least Squares GAN (LSGAN), GANs with the hinge loss.
Stars: ✭ 42 (-57.14%)
Mutual labels:  generative-adversarial-network
CPCE-3D
Low-dose CT via Transfer Learning from a 2D Trained Network, In IEEE TMI 2018
Stars: ✭ 40 (-59.18%)
Mutual labels:  generative-adversarial-network
AdversarialBinaryCoding4ReID
Codes of the paper "Adversarial Binary Coding for Efficient Person Re-identification"
Stars: ✭ 12 (-87.76%)
Mutual labels:  generative-adversarial-network
tiny-pix2pix
Redesigning the Pix2Pix model for small datasets with fewer parameters and different PatchGAN architecture
Stars: ✭ 21 (-78.57%)
Mutual labels:  generative-adversarial-network
gan-vae-pretrained-pytorch
Pretrained GANs + VAEs + classifiers for MNIST/CIFAR in pytorch.
Stars: ✭ 134 (+36.73%)
Mutual labels:  generative-adversarial-network
py-msa-kdenlive
Python script to load a Kdenlive (OSS NLE video editor) project file, and conform the edit on video or numpy arrays.
Stars: ✭ 25 (-74.49%)
Mutual labels:  generative-adversarial-network
Long-Tail-GAN
Adversarial learning framework to enhance long-tail recommendation in Neural Collaborative Filtering
Stars: ✭ 19 (-80.61%)
Mutual labels:  generative-adversarial-network
CharacterGAN
CharacterGAN: Few-Shot Keypoint Character Animation and Reposing (Best Paper WACV 2022)
Stars: ✭ 172 (+75.51%)
Mutual labels:  generative-adversarial-network
ArtGAN
Tensorflow codes for our ICIP-17 and arXiv-1708.09533 works: "ArtGAN: Artwork Synthesis with Conditional Categorial GAN" & "Learning a Generative Adversarial Network for High Resolution Artwork Synthesis "
Stars: ✭ 16 (-83.67%)
Mutual labels:  generative-adversarial-network
face inpainting
No description or website provided.
Stars: ✭ 27 (-72.45%)
Mutual labels:  generative-adversarial-network

Exemplar_GAN_Eye_Inpainting

The tensorflow implement of Eye In-Painting with Exemplar Generative Adversarial Networks

Introduction

Paper Introduction.

Network Architecture

Paper result

Noted: Differences with the original paper.

  • Because the origin paper does't provide the details of model, this implement uses the architecture and hyperparamters from SG-GAN(Using adapted residual image learning for G and spectral norm for D)

  • Just use refernece image as the exemplar, not code.

  • Our model trained using 256x256 pixels, not 128x128 mentioned in the original paper.

Dependencies

Usage

  • Clone this repo:
git clone https://github.com/zhangqianhui/Exemplar_GAN_Eye_Inpainting.git
  • Download the CelebA-ID dataset

You can download CelebA-ID Benchmark dataset according to the Dataset

and unzip CelebA-ID into a directory.

  • Train the model using the default parameter
python main.py --OPER_FLAG=0 --path your_path
  • Test the model
python main.py --OPER_FLAG=1 --path your_path --test_step= your model_name

Our results

(1)Input image; (2) Reference image; (3) image to in-paint; (4) in-painted image; (5) local real eye region; (6) generated eye region;

Different reference images

Reference code

Sparsely_Grouped_GAN

DCGAN tensorflow

Spectral Norm tensorflow

Similar project

Eye_Rotation_GAN

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].