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.
DragGAN 是一个AI图像编辑工具,通过鼠标拉伸图像即可自动生成新图像
SoftVC VITS Singing Voice Conversion
#计算机科学# Image-to-Image Translation in PyTorch
翻译 - PyTorch中的图像到图像翻译
Bringing Old Photo Back to Life (CVPR 2020 oral)
翻译 - 重现旧照片(CVPR 2020口头)
#计算机科学# A list of all named GANs!
翻译 - 所有已命名GAN的列表!
#计算机科学# MMagic (Multimodal Advanced, Generative, and Intelligent Creation) 是一个供专业人工智能研究人员和机器学习工程师去处理、编辑和生成图像与视频的开源 AIGC 工具箱
#计算机科学# Synthesizing and manipulating 2048x1024 images with conditional GANs
翻译 - 使用条件GAN合成和处理2048x1024图像
#计算机科学# Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement
翻译 - Pytorch中Stylegan2最简单的工作实现
#计算机科学# [CVPR2020] Adversarial Latent Autoencoders
翻译 - [CVPR2020]对抗性潜在自动编码器
#计算机科学# StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.
翻译 - StudioGAN是一个Pytorch库,为有条件/无条件图像生成提供了代表性的生成对抗网络(GAN)的实现。
DeepFill v1/v2 with Contextual Attention and Gated Convolution, CVPR 2018, and ICCV 2019 Oral
翻译 - 具有上下文注意和门控卷积的DeepFill v1 / v2,CVPR 2018和ICCV 2019 Oral
Official Implementation for "Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation" (CVPR 2021) presenting the pixel2style2pixel (pSp) framework
翻译 - “样式编码:用于图像到图像翻译的StyleGAN编码器”的官方实现
Diffusion model papers, survey, and taxonomy
#计算机科学# Synthetic data generation for tabular data
翻译 - 表格、关系和时间序列数据的合成数据生成。
Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)
翻译 - 对比性的非配对图像到图像翻译,比cyclegan更快,更轻松的训练(ECCV 2020,在PyTorch中)
MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV.
翻译 - MMGeneration是基于PyTorch和MMCV的强大的生成模型工具包。
#计算机科学# Implementation of GigaGAN, new SOTA GAN out of Adobe. Culmination of nearly a decade of research into GANs
#计算机科学# Discovering Interpretable GAN Controls [NeurIPS 2020]
翻译 - 发现可解释的GaN控制[Neurips 2020]
#计算机科学# One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more