Improving Continuous Normalizing Flows using a Multi-Resolution Framework

Vikram Voleti, Chris Finlay, Adam M Oberman, Christopher Pal

Keywords: generative models, continuous normalizing flows

TL;DR: We introduce a multi-resolution variant to continuous normalizing flows

Abstract: Recent work has shown that Continuous Normalizing Flows (CNFs) can serve as generative models of images with exact likelihood calculation and invertible generation/density estimation. In this work we introduce a Multi-Resolution variant of such models (MRCNF). We introduce a transformation between resolutions that allows for no change in the log likelihood. We show that this approach yields comparable likelihood values for various image datasets, with improved performance at higher resolutions, with fewer parameters, using only 1 GPU.