VQ-VAE-2 is a type of variational autoencoder that combines a a two-level hierarchical VQ-VAE with a self-attention autoregressive model (PixelCNN) as a prior. The encoder and decoder architectures are kept simple and light-weight as in the original VQ-VAE, with the only difference that hierarchical multi-scale latent maps are used for increased resolution.
Source: Generating Diverse High-Fidelity Images with VQ-VAE-2Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Image Generation | 2 | 20.00% |
Quantization | 1 | 10.00% |
Change Detection | 1 | 10.00% |
Motion Planning | 1 | 10.00% |
Object Detection | 1 | 10.00% |
Object Tracking | 1 | 10.00% |
Scene Change Detection | 1 | 10.00% |
Scene Understanding | 1 | 10.00% |
Image Reconstruction | 1 | 10.00% |