AI Paper Atlas

Research map / Video / Video generation

GLOBER: Coherent Non-autoregressive Video Generation via GLOBal Guided Video DecodER

Mingzhen Sun, Weining Wang, Zihan Qin, Jiahui Sun, Sihan Chen, Jing Liu

NeurIPS 2023 · Video › Video generation · approach: Autoregressive long video generation · 0 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 CRA loss to video auto-encoder training (ablation)GLOBER · UCF-101FVD: reduction of 37.0Improved
add CRA loss to video auto-encoder training (ablation)GLOBER · Sky Time-lapseFVD: reduction of 20.8Improved
add CRA loss to video auto-encoder training (ablation)GLOBER · TaiChi-HDFVD: reduction of 31.2Improved
global feature shape 8x8x64 -> 16x16x16 (ablation)GLOBER · UCF-101FVD_gen: 725.1 -> 560.4Improved
global feature channels 16 -> 32 at 16x16 (ablation)GLOBER · UCF-101FVD_gen: 560.4 -> 521.2Improved
unconditional guidance scale mu 0 -> 6 (reconstruction) (ablation)GLOBER video decoder · UCF-101 256^2FVD: 211.4 -> 106.7Improved
unconditional guidance scale mu 6 -> 15 (reconstruction) (ablation)GLOBER video decoder · UCF-101 256^2FVD: 106.7 -> 670.8Hurt
unconditional guidance scale mu 0 -> 12 (generation) (ablation)GLOBER video generator · UCF-101 256^2FVD: 575.6 -> 168.9Improved
unconditional guidance scale mu 12 -> 15 (generation) (ablation)GLOBER video generator · UCF-101 256^2FVD: 168.9 -> 224.3Hurt
non-autoregressive generation vs VIDM autoregressive, 128 framesGLOBER · UCF-101 128-frameFVD: 1531.9 -> 1177.4Improved
GLOBER vs VideoFusion sampling speed at F=64GLOBER · 256^2 samplingtime: 76s -> 21sImproved
GLOBER vs StyleGAN-V on Sky Time-lapseGLOBER · Sky Time-lapseFVD: 79.5 -> 78.1No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 6 of 6 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