Glow: Generative Flow with Invertible 1x1 Convolutions
This work addresses the need for more efficient and high-quality generative models in machine learning, offering a novel method that enhances performance and scalability.
The authors tackled the problem of improving flow-based generative models by introducing Glow, which uses invertible 1x1 convolutions, resulting in a significant improvement in log-likelihood on standard benchmarks and enabling efficient realistic synthesis of large images.
Flow-based generative models (Dinh et al., 2014) 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 an invertible 1x1 convolution. Using our method we demonstrate a significant improvement in log-likelihood on standard benchmarks. Perhaps most strikingly, we demonstrate that a generative model optimized towards the plain log-likelihood objective is capable of efficient realistic-looking synthesis and manipulation of large images. The code for our model is available at https://github.com/openai/glow