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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use B-spline parameterization instead of plain MLP in C4DD (ablation) | SeeU · SeeU45 unseen temporal | PSNR: 17.5372 -> 20.1626 | Improved |
| use B-spline parameterization instead of plain MLP in C4DD (ablation) | SeeU · SeeU45 unseen spatial | EE: 0.3125 -> 0.2044 | Improved |
| add physics-informed loss (ablation) | SeeU · SeeU45 unseen spatial | CLIP-V: 0.9198 -> 0.9551 | Improved |
| add physics-informed loss (ablation) | SeeU · SeeU45 unseen temporal | PSNR: 19.3593 -> 20.1626 | Improved |
| increase input frames from 5 to 20 (ablation) | SeeU · SeeU45 unseen temporal | PSNR: 18.3583 -> 21.0832 | Improved |
| increase input frames from 10 to 15 (ablation) | SeeU · SeeU45 unseen temporal | PSNR: 20.1626 -> 20.3870 | No clear effect |
| use SeeU instead of ReCamMaster for camera-controlled generation | SeeU · SeeU45 dolly out | EIR: 0.6736 -> 0.7848 | Improved |
| use SeeU instead of InterpAny for interpolation | SeeU · SeeU45 dynamic frame interpolation | PSNR: 20.5406 -> 21.0726 | Improved |
| use SeeU vs Cosmos Predict2.5 for future prediction | SeeU · SeeU45 future frame prediction | PSNR: 20.0672 -> 20.5353 | Improved |
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.
- ReCamMaster — ReCamMaster: Camera-Controlled Generative Rendering from A Single Video (ICCV 2025) · better on 2 of 2 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
- Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding (NeurIPS 2025 · similarity 0.88)
- 4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time (NeurIPS 2025 · similarity 0.87)
- Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting (ICLR 2024 · similarity 0.87)
- Can 4D Foundation Models Remember? (NeurIPS 2026 · similarity 0.87)
- DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos (NeurIPS 2024 · similarity 0.87)
- DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling (NeurIPS 2025 · similarity 0.87)
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.
