Official Implementation for the paper Deep Domain Adaptation: A Sim2Real Neural Approach for Improving Eye-Tracking System.

DeepNude's algorithm and general image generation theory and practice research, including pix2pix, CycleGAN, UGATIT, DCGAN, SinGAN, ALAE, mGANprior, StarGAN-v2 and VAE models (TensorFlow2 implementation). DeepNude的算法以及通用生成对抗网络（GAN,Generative Adversarial Network）图像生成的理论与实践研究。

A deep learning model to age faces in the wild, currently runs at 60+ fps on GPUs

A (clean) PyTorch implementation of CycleGAN on Horse2zebra dataset

🖼️ Our CycleGAN Implementation for Image-to-Image Translation project leverages PyTorch to seamlessly transform images between domains, all without paired examples. With a keen focus on innovation and effectiveness, we've explored CycleGAN's capabilities across various domains. Join us as we delve into the world of image translation technology! 🚀

Advanced Study of VAEs and GANs using a Colored MNIST Dataset.

Gender Change of faces implemented with CycleGAN (in Keras) for Deep Learning Course

Translating Synthetic RIRs to Real RIRs

PyTorch implementation of the paper "Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-based Image Retrieval", CVPR 2019.

Implementation of Cycle-consistent Generative Adversarial Networks for Image-to-Image Translation in Keras

Pixel-level domain adaptation: A study case on generating parking-slot image samples.

Pytorch implementation of Self Attentive Adversarial Stain Normalization (SAASN).

Domain adaptation with cycle-gan

Cycle-Consistent Adversarial Networks (CycleGAN) using Tensorflow 2.0

Implementation of [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://arxiv.org/abs/1703.10593v6) with Tensorflow 2.x

This repository is about different types of GANs in pytorch, their proper settings and training results

PyTorch implementation of the Cycle GAN paper.

Attention based Single Image Dehazing Using Improved CycleGAN

This repository contains an implementation of the Cylce-GAN architecture for style transfer along with instructions to train on an own dataset.

A novel data augmentation method based on Cycle-GAN, and a new offline handwritten signature verification system based on CapsNet.