AI Paper Atlas

Research map / Video / Video generation

PerpetualWonder: Long-horizon Action-conditioned 4D Scene Generation

Jiahao Zhan, Zizhang Li, Hong-Xing Yu, Jiajun Wu

CVPR 2026 · Video › Video generation · approach: Trajectory-guided motion control · 11 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 VPP (physics particles anchoring Gaussians) instead of standard 3D Gaussians for the foreground (ablation)PerpetualWonder foreground · multi-view optimization, qualitativedynamics plausibilityImproved
add progressive multi-view optimization instead of direct optimization from all views at once (ablation)PerpetualWonder backward optimization · multi-view consistency, qualitativemulti-view consistencyImproved
propagate generative refinements back to physics particles (closed loop) instead of resetting Gaussians each windowhybrid generative simulator, long-horizon · castle scene, four-round interactionshape integrityImproved
use PerpetualWonder instead of WonderPlayhybrid generative simulator · 10 scenes, WorldScoreCamera Controllability: 75.95 -> 93.26Improved
use PerpetualWonder instead of WonderPlayhybrid generative simulator · 10 scenes, WorldScore3D Consistency: 63.93 -> 80.41Improved
use PerpetualWonder instead of WonderPlayhybrid generative simulator · 10 scenes, WorldScoreImaging Quality: 36.80 -> 66.98Improved
use PerpetualWonder instead of Veo3.1video generation baseline · 10 scenes, WorldScoreImaging Quality: 67.82 -> 66.98No clear effect
use PerpetualWonder instead of Veo3.1video generation baseline · 2AFC human studyfavor rate (%): 62.0% physics plausibility, 70.8% motion fidelityImproved

Later papers that compared with this method

1 later accepted paper reports PerpetualWonder as a baseline in their results tables; 1 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