All Projects → ddtm → Deep Smile Warp

ddtm / Deep Smile Warp

Licence: mit
DeepWarp for Facial Expression Manipulation

Programming Languages

lua
6591 projects

Projects that are alternatives of or similar to Deep Smile Warp

Glitch This
📷 Glitchify images and GIF - with highly customizable options!
Stars: ✭ 1,396 (+812.42%)
Mutual labels:  image-manipulation
Gandissect
Pytorch-based tools for visualizing and understanding the neurons of a GAN. https://gandissect.csail.mit.edu/
Stars: ✭ 1,700 (+1011.11%)
Mutual labels:  image-manipulation
Focal Frequency Loss
Focal Frequency Loss for Generative Models
Stars: ✭ 141 (-7.84%)
Mutual labels:  image-manipulation
Zebra image
A compact (one-file only) and lightweight PHP library for image manipulation providing methods for performing several types of image manipulation operations and applying filters to images
Stars: ✭ 108 (-29.41%)
Mutual labels:  image-manipulation
Bitmap
C++ Bitmap Library
Stars: ✭ 125 (-18.3%)
Mutual labels:  image-manipulation
Nuxt Image Loader Module
An image loader module for nuxt.js that allows you to configure image style derivatives.
Stars: ✭ 135 (-11.76%)
Mutual labels:  image-manipulation
Lggan
[CVPR 2020] Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
Stars: ✭ 97 (-36.6%)
Mutual labels:  image-manipulation
Genegan
GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data
Stars: ✭ 142 (-7.19%)
Mutual labels:  image-manipulation
Cloudinary java
Cloudinary Java Client Library
Stars: ✭ 131 (-14.38%)
Mutual labels:  image-manipulation
Avir
High-quality pro image resizing / scaling C++ library, image resize
Stars: ✭ 135 (-11.76%)
Mutual labels:  image-manipulation
L1stabilizer
🎥 Video stabilization using L1-norm optimal camera paths.
Stars: ✭ 111 (-27.45%)
Mutual labels:  image-manipulation
Cyclegan
Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.
Stars: ✭ 10,933 (+7045.75%)
Mutual labels:  image-manipulation
Oneshottranslation
Pytorch implementation of "One-Shot Unsupervised Cross Domain Translation" NIPS 2018
Stars: ✭ 135 (-11.76%)
Mutual labels:  image-manipulation
Neural Doodle
Turn your two-bit doodles into fine artworks with deep neural networks, generate seamless textures from photos, transfer style from one image to another, perform example-based upscaling, but wait... there's more! (An implementation of Semantic Style Transfer.)
Stars: ✭ 9,680 (+6226.8%)
Mutual labels:  image-manipulation
Tsit
[ECCV 2020 Spotlight] A Simple and Versatile Framework for Image-to-Image Translation
Stars: ✭ 141 (-7.84%)
Mutual labels:  image-manipulation
Exprgan
Facial Expression Editing with Controllable Expression Intensity
Stars: ✭ 98 (-35.95%)
Mutual labels:  image-manipulation
Combogan
Stars: ✭ 134 (-12.42%)
Mutual labels:  image-manipulation
Wallgen
Generate HQ poly wallpapers
Stars: ✭ 153 (+0%)
Mutual labels:  image-manipulation
Starnet
StarNet
Stars: ✭ 141 (-7.84%)
Mutual labels:  image-manipulation
Gesturegan
[ACM MM 2018 Oral] GestureGAN for Hand Gesture-to-Gesture Translation in the Wild
Stars: ✭ 136 (-11.11%)
Mutual labels:  image-manipulation

DeepWarp for Facial Expression Manipulation

Warning: the repo is under construction so the code may not be runnable out of the box!

This is a repository containing torch7 code implementing DeepWarp. Be sure to check out the online demo. Due to licensing restrictions I'm not able to release the original gaze manipulation code and corresponding dataset, but the model presented here is very similar and you are free to use it as a reference point.

Showcase

To showcase general applicability of the approach, I'm using an ever so slightly modified network to handle smile addition and removal in the images containg human faces.

Model

The model (shown above) contains three networks:

  • Transformer T. Warps the image given δ which is either +1 (add smile) or -1 (remove smile)
  • Discriminator D. Makes sure that the warped output looks plausible.
  • Attribute branch A. Infers attribute (1 for "smile", -1 for "no smile") value given an image.

The training objective is a weighted sum of two components:

where the first term is called the attribute loss and is a standard GAN cost.

Citation

Please cite the DeepWarp paper in your publications if this repo helps your research:

@inproceedings{ganin2016deepwarp,
  title={DeepWarp: Photorealistic image resynthesis for gaze manipulation},
  author={Ganin, Yaroslav and Kononenko, Daniil and Sungatullina, Diana and Lempitsky, Victor},
  booktitle={European Conference on Computer Vision},
  pages={311--326},
  year={2016},
  organization={Springer}
}
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].