Can Your Model Separate Yolks with a Water Bottle? Benchmarking Physical Commonsense Understanding in Video Generation Models

• URL: http://arxiv.org/abs/2507.15824v1
• Date: Mon, 21 Jul 2025 17:30:46 GMT
• Title: Can Your Model Separate Yolks with a Water Bottle? Benchmarking Physical Commonsense Understanding in Video Generation Models
• Authors: Enes Sanli, Baris Sarper Tezcan, Aykut Erdem, Erkut Erdem,
• Abstract summary: We present PhysVidBench, a benchmark designed to evaluate the physical reasoning capabilities of text-to-video systems.<n>For each prompt, we generate videos using diverse state-of-the-art models and adopt a three-stage evaluation pipeline.<n> PhysVidBench provides a structured, interpretable framework for assessing physical commonsense in generative video models.
• Score: 14.187604603759784
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent progress in text-to-video (T2V) generation has enabled the synthesis of visually compelling and temporally coherent videos from natural language. However, these models often fall short in basic physical commonsense, producing outputs that violate intuitive expectations around causality, object behavior, and tool use. Addressing this gap, we present PhysVidBench, a benchmark designed to evaluate the physical reasoning capabilities of T2V systems. The benchmark includes 383 carefully curated prompts, emphasizing tool use, material properties, and procedural interactions, and domains where physical plausibility is crucial. For each prompt, we generate videos using diverse state-of-the-art models and adopt a three-stage evaluation pipeline: (1) formulate grounded physics questions from the prompt, (2) caption the generated video with a vision-language model, and (3) task a language model to answer several physics-involved questions using only the caption. This indirect strategy circumvents common hallucination issues in direct video-based evaluation. By highlighting affordances and tool-mediated actions, areas overlooked in current T2V evaluations, PhysVidBench provides a structured, interpretable framework for assessing physical commonsense in generative video models.

Related papers

• Think Before You Diffuse: LLMs-Guided Physics-Aware Video Generation [28.79821758835663]
  We propose DiffPhy, a generic framework that enables physically-correct and photo-realistic video generation.<n>Our method leverages large language models (LLMs) to explicitly reason a comprehensive physical context from the text prompt.<n>We also establish a high-quality physical video dataset containing diverse phyiscal actions and events to facilitate effective finetuning.
  arXiv  Detail & Related papers  (2025-05-27T18:26:43Z)
• T2VPhysBench: A First-Principles Benchmark for Physical Consistency in Text-to-Video Generation [12.120541052871486]
  generative models produce high-quality videos that excel in aesthetic appeal and accurate instruction following.<n>Many outputs still violate basic constraints such as rigid-body collisions, energy conservation, and gravitational dynamics.<n>Existing physical-evaluation benchmarks rely on automatic, pixel-level metrics applied to simplistic, life-scenario prompts.<n>We introduce textbfT2VPhysBench, a first-principled benchmark that systematically evaluates whether state-of-the-art text-to-video systems obey twelve core physical laws.
  arXiv  Detail & Related papers  (2025-05-01T06:34:55Z)
• VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation [66.58048825989239]
  VideoPhy-2 is an action-centric dataset for evaluating physical commonsense in generated videos.<n>We perform human evaluation that assesses semantic adherence, physical commonsense, and grounding of physical rules in the generated videos.<n>Our findings reveal major shortcomings, with even the best model achieving only 22% joint performance.
  arXiv  Detail & Related papers  (2025-03-09T22:49:12Z)
• TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models [75.42002690128486]
  TemporalBench is a new benchmark dedicated to evaluating fine-grained temporal understanding in videos. It consists of 10K video question-answer pairs, derived from 2K high-quality human annotations detailing the temporal dynamics in video clips. Results show that state-of-the-art models like GPT-4o achieve only 38.5% question answering accuracy on TemporalBench.
  arXiv  Detail & Related papers  (2024-10-14T17:59:58Z)
• Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation [51.750634349748736]
  Text-to-video (T2V) models have made significant strides in visualizing complex prompts. However, the capacity of these models to accurately represent intuitive physics remains largely unexplored. We introduce PhyGenBench to evaluate physical commonsense correctness in T2V generation.
  arXiv  Detail & Related papers  (2024-10-07T17:56:04Z)
• PhyBench: A Physical Commonsense Benchmark for Evaluating Text-to-Image Models [50.33699462106502]
  Text-to-image (T2I) models frequently fail to produce images consistent with physical commonsense. Current T2I evaluation benchmarks focus on metrics such as accuracy, bias, and safety, neglecting the evaluation of models' internal knowledge. We introduce PhyBench, a comprehensive T2I evaluation dataset comprising 700 prompts across 4 primary categories: mechanics, optics, thermodynamics, and material properties.
  arXiv  Detail & Related papers  (2024-06-17T17:49:01Z)
• VideoPhy: Evaluating Physical Commonsense for Video Generation [93.28748850301949]
  We present VideoPhy, a benchmark designed to assess whether the generated videos follow physical commonsense for real-world activities. We then generate videos conditioned on captions from diverse state-of-the-art text-to-video generative models. Our human evaluation reveals that the existing models severely lack the ability to generate videos adhering to the given text prompts.
  arXiv  Detail & Related papers  (2024-06-05T17:53:55Z)
• TPA-Net: Generate A Dataset for Text to Physics-based Animation [27.544423833402572]
  We present an autonomous data generation technique and a dataset, which intend to narrow the gap with a large number of multi-modal, 3D Text-to-Video/Simulation (T2V/S) data. We take advantage of state-of-the-art physical simulation methods to simulate diverse scenarios, including elastic deformations, material fractures, collisions, turbulence, etc. High-quality, multi-view rendering videos are supplied for the benefit of T2V, Neural Radiance Fields (NeRF), and other communities.
  arXiv  Detail & Related papers  (2022-11-25T04:26:41Z)
• Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language [92.7638697243969]
  We propose a unified framework that can jointly learn visual concepts and infer physics models of objects from videos and language. This is achieved by seamlessly integrating three components: a visual perception module, a concept learner, and a differentiable physics engine.
  arXiv  Detail & Related papers  (2021-10-28T17:59:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.