AI实战：生成对抗网络 GAN 开源代码汇总

生成对抗网络 GAN 在机器视觉中的应用开源代码汇总

• CycleGAN and pix2pix in PyTorch

  • star： 12.7 K
  • 地址：https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix
  • 论文地址：https://arxiv.org/pdf/1703.10593.pdf
  • 示例图
    
    

• pix2pixHD

  • star： 4.7 K
  • 地址：https://github.com/NVIDIA/pix2pixHD
  • 介绍
    Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic image-to-image translation. It can be used for turning semantic label maps into photo-realistic images or synthesizing portraits from face label maps.
    论文地址：https://arxiv.org/abs/1609.03552

• iGAN: Interactive Image Generation via Generative Adversarial Networks （基于生成对抗网络的交互式图像生成）

  • star： 3.7 K
  • 地址：https://github.com/junyanz/iGAN
  • 简介
    iGAN (aka. interactive GAN) is the author’s implementation of interactive image generation interface described in: “Generative Visual Manipulation on the Natural Image Manifold”
    Given a few user strokes, our system could produce photo-realistic samples that best satisfy the user edits in real-time. Our system is based on deep generative models such as Generative Adversarial Networks (GAN) and DCGAN.
    论文地址：https://arxiv.org/pdf/1905.01164.pdf

• SinGAN

  • star： 2.5 K
  • 地址：https://github.com/tamarott/SinGAN
  • 简介
    Official pytorch implementation of the paper: “SinGAN: Learning a Generative Model from a Single Natural Image”
    With SinGAN, you can train a generative model from a single natural image, and then generate random samples form the given image.

• AnimeGAN

  • star： 2.1 K
  • 地址：https://github.com/TachibanaYoshino/AnimeGAN
  • 简介
    Multimodal UNsupervised Image-to-image Translation
    论文地址：https://arxiv.org/abs/1804.04732

• MUNIT

  • star： 2.1 K
  • 地址：https://github.com/NVlabs/MUNIT
  • 简介
    论文地址：https://arxiv.org/abs/1804.04732

• DeblurGAN

  • star： 1.7 K
  • 地址：https://github.com/KupynOrest/DeblurGAN
  • 简介
    Pytorch implementation of the paper DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks.
    论文地址：https://arxiv.org/pdf/1711.07064.pdf