# Physics Question Scene Graph: Fine-grained Evaluation of Physical Plausibility in Text-to-Video Generation

arXiv: https://arxiv.org/abs/2606.25306 · HTML: https://mlsanity.com/paper/2606.25306/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 53 references that are in the map.
- First posted on arXiv 24 Jun 2026.

## Builds on (most cited first, 30 of 43)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [EvalCrafter: Benchmarking and Evaluating Large Video Generation Models](https://mlsanity.com/paper/2310.11440/) (2023)
- [Optimizing Prompts for Text-to-Image Generation](https://mlsanity.com/paper/2212.09611/) (2022)
- [World Simulation with Video Foundation Models for Physical AI](https://mlsanity.com/paper/2511.00062/) (2025)
- [VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation](https://mlsanity.com/paper/2406.15252/) (2024)
- [Do LLMs exhibit human-like response biases? A case study in survey design](https://mlsanity.com/paper/2311.04076/) (2023)
- [PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation](https://mlsanity.com/paper/2409.18964/) (2024)
- [Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation](https://mlsanity.com/paper/2410.05363/) (2024)
- [Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation](https://mlsanity.com/paper/2310.18235/) (2023)
- [Do generative video models understand physical principles?](https://mlsanity.com/paper/2501.09038/) (2025)
- [Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models](https://mlsanity.com/paper/2405.04233/) (2024)
- [PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding](https://mlsanity.com/paper/2501.16411/) (2025)
- [VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation](https://mlsanity.com/paper/2503.06800/) (2025)
- [Improving Text-to-Image Consistency via Automatic Prompt Optimization](https://mlsanity.com/paper/2403.17804/) (2024)
- [Force Prompting: Video Generation Models Can Learn and Generalize Physics-based Control Signals](https://mlsanity.com/paper/2505.19386/) (2025)
- [VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior](https://mlsanity.com/paper/2503.23368/) (2025)
- [PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop](https://mlsanity.com/paper/2503.09595/) (2025)
- [MotionCraft: Physics-based Zero-Shot Video Generation](https://mlsanity.com/paper/2405.13557/) (2024)
- [PhysMotion: Physics-Grounded Dynamics From a Single Image](https://mlsanity.com/paper/2411.17189/) (2024)
- [PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation](https://mlsanity.com/paper/2509.20358/) (2025)

## Built on by (most cited first, 2 of 2)

- [PhysicsLENS: Diagnosing Physical Property Blindness in Video Generation Models](https://mlsanity.com/paper/2610.01162/) (2026)
- [PhysCodeGym: Benchmarking Coding Agents for Physically Verifiable 4D Reconstruction](https://mlsanity.com/paper/2610.17288/) (2026)

## Abstract (arXiv)

Video generation models are increasingly capable of producing realistic videos, but they still struggle to generate videos that follow basic physical laws. Compounding this is a lack of reliable granular evaluation methods for localizing and specifying physical law violations in videos. We address this by introducing Physics Question Scene Graph (PQSG), a hierarchical question-based evaluation pipeline. PQSG evaluates generated videos by checking their faithfulness to a prompt across objects, actions, and adherence to physical laws using a graph-based hierarchy of questions generated by a vision-language model (VLM), guided by high-quality in-context examples. By representing questions as a graph, PQSG introduces logical dependencies within questions, ensuring that each query is contextually valid. Moreover, PQSG provides granular assessments of which qualities of the video violate physical plausibility constraints. We validate PQSG by creating FinePhyEval, a dataset with physics-based prompts and corresponding generated videos from diverse state-of-the-art video generation models (Sora 2, Veo 3, and Wan 2.1), with each video annotated across multiple categories by humans. Using FinePhyEval, we measure the correlation between PQSG's fine-grained scores and human judgments, showing higher overall correlations than prior work. We also find that PQSG ranks closed-source models higher than Wan 2.1 on physical realism. Lastly, we show that the annotations we provide in FinePhyEval can also be used for subtask evaluation: we benchmark two strong VLMs on generating and answering questions, finding that while models can create human-like questions, they still fall short of human performance in answering them.