Generative Adversarial Networks
An AI-generated review of the GAN framework, in which a generator and a discriminator compete to produce realistic data — one of the most influential ideas.
5 steps · about 40 min · 2014–2021
From adversarial training to score-based diffusion and latent synthesis, plus the representation learning and scene models that made controllable generation possible.
Prefer to jump around? Each step is a standalone report with its own citations, figures and FAQ.
An AI-generated review of the GAN framework, in which a generator and a discriminator compete to produce realistic data — one of the most influential ideas.
An AI-generated review of DDPM, the 2020 paper that turned diffusion models into the leading family of generative models for images.
An AI-generated review of Latent Diffusion Models, the 2021 work that made text-to-image generation efficient and became the engine behind Stable Diffusion.
An AI-generated review of CLIP, the contrastive vision-language model that made zero-shot image classification and text-guided image understanding practical.
An AI-generated review of NeRF, the 2020 method that represents a 3D scene as a neural field and renders photorealistic novel views from sparse input photos.