AI Paper Atlas

Research map / Video / Video generation

SeeU: Seeing the Unseen World via 4D Dynamics-aware Generation

Yu Yuan, Tharindu Wickremasinghe, Zeeshan Nadir, Xijun Wang, Yiheng Chi, Stanley H. Chan

CVPR 2026 · Video › Video generation · approach: World-model video generation · 4 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 B-spline parameterization instead of plain MLP in C4DD (ablation)SeeU · SeeU45 unseen temporalPSNR: 17.5372 -> 20.1626Improved
use B-spline parameterization instead of plain MLP in C4DD (ablation)SeeU · SeeU45 unseen spatialEE: 0.3125 -> 0.2044Improved
add physics-informed loss (ablation)SeeU · SeeU45 unseen spatialCLIP-V: 0.9198 -> 0.9551Improved
add physics-informed loss (ablation)SeeU · SeeU45 unseen temporalPSNR: 19.3593 -> 20.1626Improved
increase input frames from 5 to 20 (ablation)SeeU · SeeU45 unseen temporalPSNR: 18.3583 -> 21.0832Improved
increase input frames from 10 to 15 (ablation)SeeU · SeeU45 unseen temporalPSNR: 20.1626 -> 20.3870No clear effect
use SeeU instead of ReCamMaster for camera-controlled generationSeeU · SeeU45 dolly outEIR: 0.6736 -> 0.7848Improved
use SeeU instead of InterpAny for interpolationSeeU · SeeU45 dynamic frame interpolationPSNR: 20.5406 -> 21.0726Improved
use SeeU vs Cosmos Predict2.5 for future predictionSeeU · SeeU45 future frame predictionPSNR: 20.0672 -> 20.5353Improved

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