【VQGAN论文精读】Taming Transformers for High-Resolution Image Synthesis

【VQGAN论文精读】Taming Transformers for High-Resolution Image Synthesis

  • 0、前言
  • Abstract
  • 1. Introduction
  • 2. Related Work
  • 3. Approach
    • 3.1. Learning an Effective Codebook of Image Constituents for Use in Transformers学习一个有效的图像成分的Codebook为了在Transformers中使用
      • 3.1.1Learning a Perceptually Rich Codebook
    • 3.2. Learning the Composition of Images with Transformers
      • 3.2.1 Latent Transformers

你可能感兴趣的:(扩散模型+CV与NLP科研笔记,人脸相关科研笔记【AI换脸】,深度学习,计算机视觉,人工智能,VQGAN,生成模型)