1、生成对抗网络(GANs):GANs是一种流行的AI画图方法,通过两个神经网络(生成器和判别器)的竞争来生成图像。生成器试图生成逼真的图像,而判别器则试图区分真实图像和生成的图像。相关的论文包括:
* Generative Adversarial Networks by Ian Goodfellow et al、(2014)
* Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks by Alec Radford et al、(2016)
2、变分自编码器(VAEs):VAEs是一种利用概率模型生成图像的方法。它们通过学习图像的潜在表示来生成新的图像。相关的论文包括:
* AutoEncoding Variational Bayes by Diederik P、Kingma et al、(2014)
* Stochastic Gradient VB and the Variational AutoEncoder by Diederik P、Kingma et al、(2014)
3、风格迁移:风格迁移是一种将一张图像的风格转移到另一张图像上的技术。相关的论文包括:
* A Neural Algorithm of Artistic Style by Leon A、Gatys et al、(2015)
* Perceptual Losses for RealTime Style Transfer and SuperResolution by Justin Johnson et al、(2016)
4、图像生成:图像生成是指利用AI生成全新的图像。相关的论文包括:
* Deep Dream: An Application of Neural Networks to Image Generation by Alexander Mordvintsev et al、(2015)
* StackGAN: Text to Photorealistic Image Synthesis with Stacked Generative Adversarial Networks by Han Zhang et al、(2017)