AI Paper Atlas

Research map / Video / Video generation

NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion

Chenfei Wu, Jian Liang, Lei Ji, Fan Yang, Yuejian Fang, Daxin Jiang, Nan Duan

ECCV 2022 · Video › Video generation · approach: Trajectory-guided motion control · 221 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 T2I pre-training to T2V (ablation)NÜWA · MSR-VTT T2VCLIPSIM: 0.2314 -> 0.2379Improved
add T2I pre-training to T2V (ablation)NÜWA · MSR-VTT T2VFID-vid: 52.98 -> 53.92Hurt
add V2V pre-training to T2V (ablation)NÜWA · MSR-VTT T2VFID-vid: 52.98 -> 51.81Improved
add V2V pre-training to T2V (ablation)NÜWA · MSR-VTT T2VCLIPSIM: 0.2314 -> 0.2335Improved
add all three tasks T2V+T2I+V2V (ablation)NÜWA · MSR-VTT T2VFID-vid: 52.98 -> 47.68Improved
use nearby attention in decoder instead of full (ablation)NÜWA · VSPW S2VFID-vid: 35.21 -> 32.06Improved
use nearby attention in encoder instead of full (ablation)NÜWA · VSPW S2VFID-vid: 35.21 -> 33.63Improved
use nearby-sparse instead of axial-sparse attention (ablation)NÜWA · VSPW S2VFID-vid: 29.18 -> 27.79Improved
use nearby-sparse instead of axial-sparse attention (ablation)NÜWA · VSPW S2VDetected PA: 0.5957 -> 0.6085Improved
use VQ-GAN instead of VQ-VAE (ablation)NÜWA · ImageNet reconstruction (256^2 to 16^2)FID: 13.3 -> 6.04Improved
use more discrete tokens (16^2 to 32^2) (ablation)NÜWA · ImageNet reconstructionFID: 6.04 -> 2.03Improved
336^2 to 21^2 tokens vs 256^2 to 16^2 at same F16 (ablation)NÜWA · ImageNet reconstructionFID: 6.04 -> 4.79Improved

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