Research map / Video / Video generation
VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior
Xindi Yang, Baolu Li, Yiming Zhang, Zhenfei Yin, Lei Bai, Liqian Ma, Zhiyong Wang, Jianfei Cai, Tien-Tsin Wong, Huchuan Lu, Xu Jia
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 |
|---|---|---|---|
| add VLM coarse motion planner (structured noise from VLM trajectories vs random noise) (ablation) | VLIPP · Physics-IQ (ablation) | Average: 16.2 -> 34.9 | Improved |
| add chain-of-thought reasoning to VLM planner (ablation) | VLIPP · Physics-IQ (ablation) | Average: 21.0 -> 34.9 | Improved |
| add in-context information to VLM planner (ablation) | VLIPP · Physics-IQ (ablation) | Average: 24.3 -> 34.9 | Improved |
| add both in-context info and CoT (ablation) | VLIPP · Physics-IQ (ablation) | Average: 18.1 -> 34.9 | Improved |
| add CoT versus add in-context info (CoT matters more) (ablation) | VLIPP · Physics-IQ (ablation) | Average: 21.0 vs 24.3 | Improved |
| add VLM-planned trajectories to I2V model vs best I2V baseline | VLIPP · PhyGenBench | Average physical score: 0.54 -> 0.60 | Improved |
| add VLM-planned trajectories vs best T2V method | VLIPP · PhyGenBench | Average physical score: 0.52 -> 0.60 | Improved |
| add VLM-planned trajectories vs SG-I2V | VLIPP · Physics-IQ | Solid Mechanics: 34.6 -> 42.3 | Improved |
| add VLM-planned trajectories vs SG-I2V | VLIPP · Physics-IQ | Fluid Dynamics: 31.2 -> 34.1 | Improved |
| add VLM-planned trajectories vs SVD-XT | VLIPP · Physics-IQ | Thermodynamics: 17.1 vs 8.8 | Hurt |
| add VLM-planned trajectories vs CogVideoX-I2V | VLIPP · User study | Physical plausibility preference: 34% -> 52% | 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.
- SG-I2V — SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation (ICLR 2025) · better on 7 of 7 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
- PHANTOM: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamics (CVPR 2026 · similarity 0.90)
- Seeing the Unseen: Unified Visible–Invisible Motion for Physically Consistent Video Generation (NeurIPS 2026 · similarity 0.90)
- How Far Is Video Generation from World Model: A Physical Law Perspective (ICML 2025 · similarity 0.89)
- LaMo: Self-Supervised Latent Motion Priors for Physical Realism in Video Generation (NeurIPS 2026 · similarity 0.88)
- VideoPhy: Evaluating Physical Commonsense for Video Generation (ICLR 2025 · similarity 0.88)
- PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation (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.
