HuiDingUMD / Exprgan
Facial Expression Editing with Controllable Expression Intensity
Stars: ✭ 98
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Exprgan
Anycost Gan
[CVPR 2021] Anycost GANs for Interactive Image Synthesis and Editing
Stars: ✭ 367 (+274.49%)
Mutual labels: gan, image-generation, image-manipulation
Lggan
[CVPR 2020] Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
Stars: ✭ 97 (-1.02%)
Mutual labels: gan, image-generation, image-manipulation
Cyclegan
Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.
Stars: ✭ 10,933 (+11056.12%)
Mutual labels: gan, image-generation, image-manipulation
Focal Frequency Loss
Focal Frequency Loss for Generative Models
Stars: ✭ 141 (+43.88%)
Mutual labels: gan, image-generation, image-manipulation
Pix2pix
Image-to-image translation with conditional adversarial nets
Stars: ✭ 8,765 (+8843.88%)
Mutual labels: gan, image-generation, image-manipulation
automatic-manga-colorization
Use keras.js and cyclegan-keras to colorize manga automatically. All computation in browser. Demo is online:
Stars: ✭ 20 (-79.59%)
Mutual labels: gan, image-manipulation, image-generation
Oneshottranslation
Pytorch implementation of "One-Shot Unsupervised Cross Domain Translation" NIPS 2018
Stars: ✭ 135 (+37.76%)
Mutual labels: gan, image-generation, image-manipulation
Tsit
[ECCV 2020 Spotlight] A Simple and Versatile Framework for Image-to-Image Translation
Stars: ✭ 141 (+43.88%)
Mutual labels: gan, image-generation, image-manipulation
Distancegan
Pytorch implementation of "One-Sided Unsupervised Domain Mapping" NIPS 2017
Stars: ✭ 180 (+83.67%)
Mutual labels: gan, image-generation, image-manipulation
Pytorch Cyclegan And Pix2pix
Image-to-Image Translation in PyTorch
Stars: ✭ 16,477 (+16713.27%)
Mutual labels: gan, image-generation, image-manipulation
Awesome-ICCV2021-Low-Level-Vision
A Collection of Papers and Codes for ICCV2021 Low Level Vision and Image Generation
Stars: ✭ 163 (+66.33%)
Mutual labels: gan, image-manipulation, image-generation
Few Shot Patch Based Training
The official implementation of our SIGGRAPH 2020 paper Interactive Video Stylization Using Few-Shot Patch-Based Training
Stars: ✭ 313 (+219.39%)
Mutual labels: gan, image-generation
Texturize
🤖🖌️ Generate photo-realistic textures based on source images. Remix, remake, mashup! Useful if you want to create variations on a theme or elaborate on an existing texture.
Stars: ✭ 366 (+273.47%)
Mutual labels: image-generation, image-manipulation
Selectiongan
[CVPR 2019 Oral] Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translation
Stars: ✭ 366 (+273.47%)
Mutual labels: image-generation, image-manipulation
Deep Generative Prior
Code for deep generative prior (ECCV2020 oral)
Stars: ✭ 308 (+214.29%)
Mutual labels: gan, image-manipulation
Sean
SEAN: Image Synthesis with Semantic Region-Adaptive Normalization (CVPR 2020, Oral)
Stars: ✭ 387 (+294.9%)
Mutual labels: gan, image-generation
Igan
Interactive Image Generation via Generative Adversarial Networks
Stars: ✭ 3,845 (+3823.47%)
Mutual labels: gan, image-manipulation
Consingan
PyTorch implementation of "Improved Techniques for Training Single-Image GANs" (WACV-21)
Stars: ✭ 294 (+200%)
Mutual labels: gan, image-generation
Apdrawinggan
Code for APDrawingGAN: Generating Artistic Portrait Drawings from Face Photos with Hierarchical GANs (CVPR 2019 Oral)
Stars: ✭ 510 (+420.41%)
Mutual labels: gan, image-generation
Hidt
Official repository for the paper "High-Resolution Daytime Translation Without Domain Labels" (CVPR2020, Oral)
Stars: ✭ 513 (+423.47%)
Mutual labels: gan, image-generation
ExprGAN
This is our Tensorflow implementation for our AAAI 2018 oral paper: "ExprGAN: Facial Expression Editing with Controllable Expression Intensity", https://arxiv.org/pdf/1709.03842.pdf
Train
- Download OULU-CASIA dataset and put the images under data folder: http://www.cse.oulu.fi/CMV/Downloads/Oulu-CASIA. split/oulu_anno.pickle contains the split of training and testing images.
- Download vgg-face.mat from matconvenet website and put it under joint-train/utils folder: http://www.vlfeat.org/matconvnet/pretrained/
- To overcome the limited training dataset, the training is consisted of three stages: a) Go inot train-controller folder to first train the controller module, run_controller.sh; b) Go into join-train folder for the second and third stage training, run_oulu.sh. Plese see our paper for more training details.
A trained model can be downloaded here: https://drive.google.com/open?id=1bz45QSdS2911-8FDmngGIyd5K4gYimzg
Test
- Run joint-train/test_oulu.sh
Citation
If you use this code for your research, please cite our paper:
@article{ding2017exprgan, title={Exprgan: Facial expression editing with controllable expression intensity}, author={Ding, Hui and Sricharan, Kumar and Chellappa, Rama}, journal={AAAI}, year={2018} }
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].