Glow: Generative Flow With Invertible 1x1 Convolutions

Authors:
Durk Kingma Google
Prafulla Dhariwal OpenAI

Introduction:

Flow-based generative models are conceptually attractive due to tractability of the exact log-likelihood, tractability of exact latent-variable inference, and parallelizability of both training and synthesis.In this paper the authors propose Glow, a simple type of generative flow using invertible 1x1 convolution.

Abstract:

Flow-based generative models are conceptually attractive due to tractability of the exact log-likelihood, tractability of exact latent-variable inference, and parallelizability of both training and synthesis. In this paper we propose Glow, a simple type of generative flow using invertible 1x1 convolution. Using our method we demonstrate a significant improvement in log-likelihood and qualitative sample quality. Perhaps most strikingly, we demonstrate that a generative model optimized towards the plain log-likelihood objective is capable of efficient synthesis of large and subjectively realistic-looking images.

You may want to know: