Bibliography (11):

1. Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images

2. https://arxiv.org/abs/1711.00937

3. Generating Diverse High-Fidelity Images with VQ-VAE-2

4. MaskGIT: Masked Generative Image Transformer

5. UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes

6. Wikipedia Bibliography:

   1. https://en.wikipedia.org/wiki/Vector_quantization  :

      https://en.wikipedia.org/wiki/Vector_quantization

   2. Latent and observable variables

   3. Autoregressive model

   4. https://en.wikipedia.org/wiki/Depth_perception  :

      https://en.wikipedia.org/wiki/Depth_perception

   5. https://en.wikipedia.org/wiki/Image_segmentation#Groups_of_image_segmentation  :

      https://en.wikipedia.org/wiki/Image_segmentation#Groups_of_image_segmentation

   6. Entropy (information theory)