Generating Diverse High-Fidelity Images with VQ-VAE-2 — mentioned by inferense

Fri, 05 Mar 2021 08:14:52 GMT

The article misses to highlight some of the important elements of the current state of the image synthesis. It's quite important to emphasise the dichotomy between the 2 current approaches in the image synthesis today. 1. Implicit distribution learning - VAE or autoregressive based techniques 2. Explicit learning of the distribution - GAN based models. The way these two model the distribution is fundamentally different. Fundamentally, GAN presents huge drawbacks when it comes to the actual inference during the synthesis. There have been dozens of models with workarounds but most of these…

Paper and discussion history. A mention is not an endorsement.

Generating Diverse High-Fidelity Images with VQ-VAE-2 — HN submission

Wed, 12 Jun 2019 13:28:43 GMT

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

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Generating Diverse High-Fidelity Images with VQ-VAE-2 · HackerPapers discussions

Generating Diverse High-Fidelity Images with VQ-VAE-2 — mentioned by inferense

Generating Diverse High-Fidelity Images with VQ-VAE-2 — HN submission