GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → shaoanlu → Fewshot Face Translation Gan

shaoanlu / Fewshot Face Translation Gan

Generative adversarial networks integrating modules from FUNIT and SPADE for face-swapping.

Labels

jupyter-notebookgangenerative-adversarial-networkimage-translation

Projects that are alternatives of or similar to Fewshot Face Translation Gan

Generative Adversarial Networks
Introduction to generative adversarial networks, with code to accompany the O'Reilly tutorial on GANs
Stars: ✭ 505 (-28.37%)
Mutual labels:  jupyter-notebook, gan, generative-adversarial-network
Dragan
A stable algorithm for GAN training
Stars: ✭ 189 (-73.19%)
Mutual labels:  jupyter-notebook, gan, generative-adversarial-network
Deep Learning With Python
Example projects I completed to understand Deep Learning techniques with Tensorflow. Please note that I do no longer maintain this repository.
Stars: ✭ 134 (-80.99%)
Mutual labels:  jupyter-notebook, gan, generative-adversarial-network
Stylegan2 Projecting Images
Projecting images to latent space with StyleGAN2.
Stars: ✭ 102 (-85.53%)
Mutual labels:  jupyter-notebook, gan, generative-adversarial-network
Sdv
Synthetic Data Generation for tabular, relational and time series data.
Stars: ✭ 360 (-48.94%)
Mutual labels:  jupyter-notebook, gan, generative-adversarial-network
Capsule Gan
Code for my Master thesis on "Capsule Architecture as a Discriminator in Generative Adversarial Networks".
Stars: ✭ 120 (-82.98%)
Mutual labels:  jupyter-notebook, gan, generative-adversarial-network
Image generator
DCGAN image generator 🖼️.
Stars: ✭ 173 (-75.46%)
Mutual labels:  jupyter-notebook, gan, generative-adversarial-network
Calogan
Generative Adversarial Networks for High Energy Physics extended to a multi-layer calorimeter simulation
Stars: ✭ 87 (-87.66%)
Mutual labels:  jupyter-notebook, gan, generative-adversarial-network
Faceswap Gan
A denoising autoencoder + adversarial losses and attention mechanisms for face swapping.
Stars: ✭ 3,099 (+339.57%)
Mutual labels:  jupyter-notebook, gan, generative-adversarial-network
IrwGAN
Official pytorch implementation of the IrwGAN for unaligned image-to-image translation
Stars: ✭ 33 (-95.32%)
Mutual labels:  generative-adversarial-network, gan, image-translation
Pixel2style2pixel
Official Implementation for "Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation"
Stars: ✭ 1,395 (+97.87%)
Mutual labels:  jupyter-notebook, generative-adversarial-network, image-translation
Deep Learning Resources
由淺入深的深度學習資源 Collection of deep learning materials for everyone
Stars: ✭ 422 (-40.14%)
Mutual labels:  jupyter-notebook, gan, generative-adversarial-network
Spectralnormalizationkeras
Spectral Normalization for Keras Dense and Convolution Layers
Stars: ✭ 100 (-85.82%)
Mutual labels:  jupyter-notebook, gan, generative-adversarial-network
Hidt
Official repository for the paper "High-Resolution Daytime Translation Without Domain Labels" (CVPR2020, Oral)
Stars: ✭ 513 (-27.23%)
Mutual labels:  jupyter-notebook, gan, generative-adversarial-network
Sprint gan
Privacy-preserving generative deep neural networks support clinical data sharing
Stars: ✭ 92 (-86.95%)
Mutual labels:  jupyter-notebook, gan, generative-adversarial-network
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 (-80.43%)
Mutual labels:  jupyter-notebook, gan, generative-adversarial-network
Alice
NIPS 2017: ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching
Stars: ✭ 80 (-88.65%)
Mutual labels:  jupyter-notebook, generative-adversarial-network, image-translation
Ganspace
Discovering Interpretable GAN Controls [NeurIPS 2020]
Stars: ✭ 1,224 (+73.62%)
Mutual labels:  jupyter-notebook, gan, generative-adversarial-network
Gan steerability
On the "steerability" of generative adversarial networks
Stars: ✭ 225 (-68.09%)
Mutual labels:  jupyter-notebook, gan, generative-adversarial-network
Simgan Captcha
Solve captcha without manually labeling a training set
Stars: ✭ 405 (-42.55%)
Mutual labels:  jupyter-notebook, gan, generative-adversarial-network
View All Similar Projects ➔

Few-shot face translation Source face: Mona Lisa

A GAN based approach for one model to swap them all.

The table below shows our priliminary face-swapping results requiring one source face and <=5 target face photos. Notice that almost all of the identities, except Stephen Curry, are not in our training data (which is a subset of VGGFace2). More translation results can be found here.

Also, our model is capable of producing faces that has its gaze direction, glasses, and hiar occlusions being consistent with given source face. However, our model has suboptimal performance in terms of translating to asian faces. This is possibly due to limited representability of the feature extractor.

Src.\Tar. Andrej Karpathy Andrew Y. Ng Du Fu Elon Musk Emilia Clarke Geoffrey Hinton Stephen Curry Yann Lecun Yoshua Benjio
Andrej
Karpathy		 N/A
Andrew
Y. Ng		 N/A
Du Fu N/A
Elon
Musk		 N/A
Emilia
Clarke		 N/A
Geoffrey
Hinton		 N/A
Stephen
Curry		 N/A
Yann
Lecun		 N/A
Yoshua
Benjio		 N/A

I really like the Du Fu translation: such an interesting demostration how the GAN imagine the appearance of the prominent Chinese poet from just a painting.

Try in Google Colab

  • master branch (Jun. 2019) Open In Colab
  • dev branch (Oct. 2019) Open In Colab
We only provide pre-trained weights and inference script for now. Training script will be released after code cleanup.

Architecture

The above image illustrates our generator, which is a encoder-decoder based network, at test phase. Our swap-them-all approach is basically a GAN conditioned on the latent embeddings extracted from a pre-trained face recognition model. SPADE and AdaIN modules are incorporated in order to inject semantic priors to the networks.

During training phase, the input face A is heavily blurred and we train the model with resonctruction loss. Other objectives that aimed to improve translation performance while keeping semantic consistency, such as perceptual loss on rgb output and cosine similarity loss on latent embeddings, are also introduced.

Things that didn't work

  1. We tried to distort (spline warp, downsample) the input image as in faceswap-GAN instead of masking it. However, the model did not learn proper identity translation but output face that is similar to its input.

Requirements

  • Python 3.6
  • Keras 2.2.4
  • TensorFlow 1.12.0 or 1.13.1

References

  1. Semantic Image Synthesis with Spatially-Adaptive Normalization
  2. Few-Shot Unsupervised Image-to-Image Translation
  3. DEEP LEARNING FOR FASHION AND FORENSICS
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].