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

Ali Razavi, Aaron van den Oord, Oriol Vinyals

Oct-2-2025, 20:17:27 GMT–Neural Information Processing Systems

We explore the use of V ector Quantized V ariational AutoEncoder (VQ-V AE) models for large scale image generation.

artificial intelligence, deep learning, machine learning, (19 more...)

Neural Information Processing Systems

Oct-2-2025, 20:17:27 GMT

Conferences PDF

Country:
- North America > Canada (0.04)

Technology:
- Information Technology
  - Artificial Intelligence
    - Machine Learning > Neural Networks
      - Deep Learning (0.69)
    - Vision (1.00)
  - Sensing and Signal Processing > Image Processing (1.00)

Duplicate Docs Excel Report

Title
Generating Diverse High-Fidelity Images with VQ-VAE-2

Similar Docs Excel Report more

Title	Similarity	Source
None found