pith. sign in

arxiv: 1807.03039 · v2 · pith:ZHW2WLZDnew · submitted 2018-07-09 · 📊 stat.ML · cs.AI· cs.LG

Glow: Generative Flow with Invertible 1x1 Convolutions

classification 📊 stat.ML cs.AIcs.LG
keywords generativeglowlog-likelihooddemonstrateexactflowinvertiblemodel
0
0 comments X
read the original abstract

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

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Guided Image Generation with Conditional Invertible Neural Networks

    cs.CV 2019-07 unverdicted novelty 7.0

    Proposes cINN architecture for conditional image generation that by construction yields diverse sharp samples, demonstrated on MNIST digit generation and image colorization with latent space manipulation.

  2. A flow-matching generative model for event-by-event jet-induced hydro response in high-energy heavy-ion collisions

    nucl-th 2026-05 unverdicted novelty 6.0

    A flow-matching generative model trained on CoLBT-hydro data conditionally generates marginal final-state hadron spectra from jet-induced hydro responses in 0-10% Pb+Pb collisions at 5.02 TeV, matching training data s...

  3. Dartmouth Stellar Evolution Emulator (DSEE) 1: Generative Stellar Evolution Model Database

    astro-ph.SR 2026-04 unverdicted novelty 6.0

    DSEE is a flow-based emulator that generates stellar evolution tracks and isochrones as probabilistic outputs from a single model trained on millions of simulations, enabling fast interpolation and uncertainty-aware analyses.

  4. Reversible Deep Learning for 13C NMR in Chemoinformatics: On Structures and Spectra

    cs.LG 2026-02 unverdicted novelty 6.0

    A conditional invertible neural network unifies forward prediction of 13C NMR spectra from structures and inverse generation of structure candidates from spectra.

  5. VideoGPT: Video Generation using VQ-VAE and Transformers

    cs.CV 2021-04 accept novelty 6.0

    VideoGPT generates competitive natural videos by learning discrete latents with VQ-VAE and modeling them autoregressively with a transformer.