ak9250's repositories
stylegan-art
train stylegan through transfer learning
gpt-2-colab
retrain gpt-2 in colab
fewshot-face-translation-GAN
Generative adversarial networks integrating modules from FUNIT and SPADE for face-swapping.
Real-Time-Voice-Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
impersonator
PyTorch implementation of our ICCV 2019 paper: Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis
Realistic-Neural-Talking-Head-Models
My implementation of Few-Shot Adversarial Learning of Realistic Neural Talking Head Models (Egor Zakharov et al.).
3d-photo-inpainting
[CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting
DeepPrivacy
DeepPrivacy: A Generative Adversarial Network for Face Anonymization
faceswap-GAN
A denoising autoencoder + adversarial losses and attention mechanisms for face swapping.
Facial_Details_Synthesis
Photo-Realistic Facial Details Synthesis from Single Image (ICCV2019 Oral)
first-order-model
This repository contains the source code for the paper First Order Motion Model for Image Animation
InterFaceGAN
Code for paper `Interpreting the Latent Space of GANs for Semantic Face Editing`
LearningToPaint
Learning to Paint with Model-based Deep Reinforcement Learning
motion-cosegmentation
Reference code for "Motion-supervised Co-Part Segmentation" paper
One_Shot_Face_Reenactment
Official test script for 2019 BMVC paper 'One-shot Face Reenactment' in PyTorch.
Photorealistic-Style-Transfer
High-Resolution Network for Photorealistic Style Transfer
PIFu
This repository contains the code for the paper "PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization"
ReshapeGAN
ReshapeGAN: Object Reshaping by Providing A Single Reference Image
selfie2anime-site
Website front-end of selfie2anime.com
stylegan-encoder
StyleGAN Encoder - converts real images to latent space
talking-heads
Our implementation of "Few-Shot Adversarial Learning of Realistic Neural Talking Head Models" (Egor Zakharov et al.)