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.
Glow: Generative Flow with Invertible 1x1 Convolutions
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
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
representative citing papers
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 statistics with approximately six orders of magnitude computational speedup.
A conditional invertible neural network unifies forward prediction of 13C NMR spectra from structures and inverse generation of structure candidates from spectra.
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.
VideoGPT generates competitive natural videos by learning discrete latents with VQ-VAE and modeling them autoregressively with a transformer.
citing papers explorer
-
Guided Image Generation with Conditional Invertible Neural Networks
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.
-
A flow-matching generative model for event-by-event jet-induced hydro response in high-energy heavy-ion collisions
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 statistics with approximately six orders of magnitude computational speedup.
-
Reversible Deep Learning for 13C NMR in Chemoinformatics: On Structures and Spectra
A conditional invertible neural network unifies forward prediction of 13C NMR spectra from structures and inverse generation of structure candidates from spectra.
-
Dartmouth Stellar Evolution Emulator (DSEE) 1: Generative Stellar Evolution Model Database
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.
-
VideoGPT: Video Generation using VQ-VAE and Transformers
VideoGPT generates competitive natural videos by learning discrete latents with VQ-VAE and modeling them autoregressively with a transformer.