Papers › Multi-Resolution Continuous Normalizing Flows

Multi-Resolution Continuous Normalizing Flows

15 Jun 2021arXiv:2106.08462archive 2025-07-28

Vikram Voleti, Chris Finlay, Adam Oberman, Christopher Pal

Recent work has shown that Neural Ordinary Differential Equations (ODEs) can serve as generative models of images using the perspective of Continuous Normalizing Flows (CNFs). Such models offer exact likelihood calculation, and invertible generation/density estimation. In this work we introduce a Multi-Resolution variant of such models (MRCNF), by characterizing the conditional distribution over the additional information required to generate a fine image that is consistent with the coarse image. 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. Further, we examine the out-of-distribution properties of (Multi-Resolution) Continuous Normalizing Flows, and find that they are similar to those of other likelihood-based generative models.

PaperPDFConference PDFCode

Code

voletiv/mrcnf officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Density EstimationImage Generation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Density Estimation CIFAR-10 MRCNF NLL (bits/dim) 3.54 #13 of 15 Archive leaderboard report
Image Generation ImageNet 32x32 MRCNF bpd 3.77 #23 of 35 Archive leaderboard report
Image Generation ImageNet 64x64 MRCNF Bits per dim 3.44 #44 of 65 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Normalizing Flows

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections