AI Paper Atlas

Research map / Video / Video generation

Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Sample

Shir Gur, Sagie Benaim, Lior Wolf

NeurIPS 2020 · Video › Video generation · approach: Autoregressive long video generation · 12 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 hp-VAE-GAN trained on one video instead of multi-sample video GANs (MoCoGAN)hp-VAE-GAN · SVFID vs 1st nearest neighbormean SVFID: 19.0 -> 6.1Improved
use hp-VAE-GAN vs TGAN when compared to a 2nd nearest neighbor videohp-VAE-GAN · SVFID vs 2nd NN, TGAN samplesmean SVFID: 20.6 -> 21.0Hurt
use hp-VAE-GAN instead of multi-sample baselineshp-VAE-GAN · UCF-101 testFID: 42.0 -> 22.1Improved
use patch-VAE for coarse scales plus patch-GAN instead of SinGAN/ConSinGAN 3D extensionhp-VAE-GAN · single-video user studydiversity MOS: 2.9 -> 3.8Improved
use hp-VAE-GAN instead of SinGAN on single-image generationhp-VAE-GAN · single-image user studyrealness MOS: 2.3 -> 3.5Improved
increase number of patch-VAE levels M (ablation)hp-VAE-GAN · single video generationdiversity vs SVFIDMixed
use only VAE levels (M=N=9) (ablation)hp-VAE-GAN · single video generationvisual qualityHurt
use a single VAE level (M=1) (ablation)hp-VAE-GAN · single video generationdiversityHurt
train all levels instead of freezing earlier networks (ablation)hp-VAE-GAN · single video generationdiversity and SVFID: diversity -51%, SVFID +680%Hurt
set decoder receptive field r=1 (ablation)patch-VAE · M=5 patch-VAE outputsample quality (qualitative)Hurt
set encoder receptive field r=1 (ablation)patch-VAE · M=5 patch-VAE outputdiversity (qualitative)Hurt
replace our patch-VAE by PatchVAE of Gupta et al. (ablation)patch-VAE · M=5 patch-VAE outputsample quality (qualitative)Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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