AI Paper Atlas

Research map / Video / Video generation

MoStGAN-V: Video Generation With Temporal Motion Styles

Xiaoqian Shen, Xiang Li, Mohamed Elhoseiny

CVPR 2023 · Video › Video generation · approach: Autoregressive long video generation · 26 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
add time-dependent motion styles with MoStAttStyleGAN-V · FaceForensics 256²FVD16: 47.4 -> 39.7Improved
add time-dependent motion styles with MoStAttStyleGAN-V · SkyTimelapse 256²FVD16: 79.5 -> 65.3Improved
add time-dependent motion styles with MoStAttStyleGAN-V · RainbowJelly 256²FVD16: 195.4 -> 70.1Improved
add time-dependent motion styles with MoStAttStyleGAN-V · CelebV-HQ 256²FVD16: 68.0 -> 56.1Improved
use one motion style without MoStAtt (ablation)MoStGAN-V · FaceForensics 256²FVD16: 39.7 -> 50.9Hurt
use one motion style without MoStAtt (ablation)MoStGAN-V · RainbowJelly 256²FVD16: 70.1 -> 248.7Hurt
use 6 motion styles instead of 8 (ablation)MoStGAN-V · RainbowJelly 256²FVD16: 70.1 -> 96.1Hurt
use 10 motion styles instead of 8 (ablation)MoStGAN-V · FaceForensics 256²FVD16: 39.7 -> 40.4Hurt
apply motion-style modulation before content-style modulation (ablation)MoStGAN-V · FaceForensics 256²FVD16: 39.76 -> 65.07Hurt
add frame differences as discriminator inputs (ablation)StyleGAN-V · FaceForensics 256²FVD16: 47.4 -> 58.1Hurt
add frame differences as discriminator inputs (ablation)MoStGAN-V · FaceForensics 256²FVD16: 49.1 -> 39.7Improved
add motion diversity loss Ldiv (ablation)MoStGAN-V · FaceForensics 256²FVD128: 79.8 -> 72.6Improved

Later papers that compared with this method

3 later accepted papers report MoStGAN-V as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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