AI Paper Atlas

Research map / Image generation / GANs

Variational Diffusion Autoencoders with Random Walk Sampling

Henry Li, Ofir Lindenbaum, Xiuyuan Cheng, Alexander Cloninger

ECCV 2020 · Image generation › GANs · approach: Generative adversarial network theory · 14 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use VDAE instead of WGANgenerative model · BulldogGromov-Wasserstein distance: 117.3 -> 15.3Improved
use VDAE instead of VAEgenerative model · BulldogFID: 245.7 -> 144.3Improved
use VDAE instead of GANgenerative model · BulldogMMD: 741.8 -> 9.68Improved
use VDAE instead of GANgenerative model · Stanford bunnyMMD: 175.6 -> 3.6Improved
use VDAE instead of WGANgenerative model · MNISTGromov-Wasserstein distance: 3.6 -> 14.4Hurt
use VDAE instead of beta-VAEgenerative model · MNISTMedian bi-Lipschitz: 1.6 -> 8.4Hurt
use VDAE instead of SVAEgenerative model · Frey facesMMD: 29.4 -> 47.0Hurt
use VDAE instead of WGANgenerative model · TorusMedian bi-Lipschitz: 3.3 -> 4.8Hurt
use VDAE instead of beta-VAEgenerative model · Stanford bunnyMedian bi-Lipschitz: 34.4 -> 5.5Improved
repeat random-walk resampling stepsVDAE sampling · synthetic manifoldsconvergence to uniform distribution: 20 steps; stationary within 5-10 iterationsImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy