Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.
-
Updated
Sep 12, 2023 - Lua
Generative adversarial networks (GAN) are a class of generative machine learning frameworks. A GAN consists of two competing neural networks, often termed the Discriminator network and the Generator network. GANs have been shown to be powerful generative models and are able to successfully generate new data given a large enough training dataset.
Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.
Image-to-image translation with conditional adversarial nets
[CVPR 2016] Unsupervised Feature Learning by Image Inpainting using GANs
Generating Videos with Scene Dynamics. NIPS 2016.
Code for "On the Effects of Batch and Weight Normalization in Generative Adversarial Networks"
Handwritten Chinese Characters Generation
Sharpness-aware Low Dose CT Denoising Using Conditional Generative Adversarial Network
SeGAN: Segmenting and Generating the Invisible (https://arxiv.org/pdf/1703.10239.pdf)
Torch implementation of various types of GAN (e.g. DCGAN, ALI, Context-encoder, DiscoGAN, CycleGAN, EBGAN, LSGAN)
Torch implementation of "PROGRESSIVE GROWING OF GANS FOR IMPROVED QUALITY, STABILITY, AND VARIATION"
Auxiliary Classifier Generative Adversarial Network in Torch7
Torch implementation of "Pixel-Level Domain Transfer"
Image-to-image translation using conditional adversarial nets
Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.
Released June 10, 2014