GEOPHYS: The Geometry of Physical Plausibility

• URL: http://arxiv.org/abs/2606.20707v1
• Date: Mon, 15 Jun 2026 20:51:35 GMT
• Title: GEOPHYS: The Geometry of Physical Plausibility
• Abstract summary: We show that indicators of physical plausibility are implicitly captured by five geometric properties of the per-frame embeddings produced by frozen image encoders.<n>We robustly discriminates physically implausible videos from realistic ones, achieving state-of-the-art physics-violation detection.<n>Ultimately, GEOPHYS demonstrates that physical plausibility in videos can be assessed by leveraging the emergent geometric properties of temporal features extracted from image encoders.
• Score: 80.0207225156318
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While humans can identify physically implausible events within milliseconds, machine learning approaches addressing the same problem are extremely slow and expensive. They either rely on external multimodal-LLM judges or require ad-hoc modifications to the training procedure. In this work, we argue that indicators of physical plausibility are implicitly captured by five geometric properties of the per-frame embeddings produced by frozen image encoders. In aggregate, we call them GEOPHYS. First, we show that these signals correlate with human EEG responses to two forms of object-permanence violations. Second, GEOPHYS robustly discriminates physically implausible videos from realistic ones, achieving state-of-the-art physics-violation detection: 98.3% on LikePhys and 93.3% on IntPhys2, whereas V-JEPA 2, GPT-4o, Gemini, and twelve modern video diffusion models perform near chance. Third, used as a best-of-N verifier for physical alignment during video generation, GEOPHYS lifts MAGI-1 24B from 50.01% to 64.50% on PhysicsIQ at 1.5x lower wall-clock and 4.65x lower memory than the V-JEPA 2 world-model verifier. Ultimately, GEOPHYS demonstrates that physical plausibility in videos can be assessed by leveraging the emergent geometric properties of temporal features extracted from image encoders.

Related papers

• Proprio: Latent Self-Scoring and Inference-Time Refinement for Physically Plausible Video Generation [78.41956766048308]
  Proprio is a training-free framework that enables a frozen generator to assess and improve the physical plausibility of its own outputs.<n>Inspired by proprioception, the biological sense of one's own movement, Proprio treats the model's flow residual as a self-scoring signal.<n>Proprio consistently improves physical plausibility across text-to-video and image-to-video benchmarks.
  arXiv  Detail & Related papers  (2026-05-27T09:44:18Z)
• PhyCo: Learning Controllable Physical Priors for Generative Motion [55.59209981836171]
  We present PhyCo, a framework that introduces continuous, interpretable, and physically grounded control into video generation.<n>Our approach integrates three key components: (i) a large-scale dataset of over 100K photorealistic simulation videos where friction, restitution, deformation, and force are systematically varied across diverse scenarios; (ii) physics-supervised fine-tuning of a pretrained diffusion model using a ControlNet conditioned on pixel-aligned physical property maps; and (iii) VLM-guided reward optimization, where a fine-tuned vision-language model evaluates generated videos with targeted physics queries and provides differentiable feedback.
  arXiv  Detail & Related papers  (2026-04-30T17:53:03Z)
• Physion-Eval: Evaluating Physical Realism in Generated Video via Human Reasoning [77.34919361116037]
  Video generation models are increasingly used as world simulators for storytelling, simulation, and embodied AI.<n>Existing evaluations largely rely on automated metrics or coarse human judgments such as preferences or rubric-based checks.<n>We introduce Physion-Eval, a benchmark of expert human reasoning for diagnosing physical realism failures in videos generated by five state-of-the-art models.
  arXiv  Detail & Related papers  (2026-03-20T03:25:41Z)
• PhysVideo: Physically Plausible Video Generation with Cross-View Geometry Guidance [31.104339154260312]
  We propose PhysVideo, a framework that generates physics-aware videos and then synthesizes full videos with background foregrounds.<n>In the first stage, Phys4View captures the influence of physical attributes on motion dynamics, and enhances spatial-temporal consistency.<n>In the second stage, Video uses the generated videos as guidance and learns the interactions between foreground dynamics and background context for controllable video synthesis.
  arXiv  Detail & Related papers  (2026-03-19T09:03:06Z)
• HOCA-Bench: Beyond Semantic Perception to Predictive World Modeling via Hegelian Ontological-Causal Anomalies [30.95227838131802]
  Video-LLMs have improved steadily on semantic perception, but they still fall short on predictive world modeling.<n>We introduce HOCA-Bench, a benchmark that frames physical anomalies through a Hegelian lens.
  arXiv  Detail & Related papers  (2026-02-23T07:40:32Z)
• PhysChoreo: Physics-Controllable Video Generation with Part-Aware Semantic Grounding [50.454084539837005]
  PhysChoreo is a novel framework that can generate videos with diverse controllability and physical realism from a single image.<n>Our method consists of two stages: first, it estimates the static initial physical properties of all objects in the image through part-aware physical property reconstruction.<n>Then, through temporally instructed and physically editable simulation, it synthesizes high-quality videos with rich dynamic behaviors and physical realism.
  arXiv  Detail & Related papers  (2025-11-25T17:59:04Z)
• Improving the Physics of Video Generation with VJEPA-2 Reward Signal [28.62446995107834]
  State-of-the-art video generative models exhibit severely limited physical understanding.<n> intuitive physics understanding has shown to emerge from SSL pretraining on natural videos.<n>We show that by leveraging VJEPA-2 as reward signal, we can improve the physics plausibility of state-of-the-art video generative models by 6%.
  arXiv  Detail & Related papers  (2025-10-22T13:40:38Z)
• PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation [53.06495362038348]
  Existing generation models excel at producing photo-realistic videos from text or images, but often lack physical plausibility and 3D controllability.<n>We introduce PhysCtrl, a novel framework for physics-grounded image-to-video generation with physical parameters and force control.<n> Experiments show that PhysCtrl generates realistic, physics-grounded motion trajectories which, when used to drive image-to-video models, yield high-fidelity, controllable videos.
  arXiv  Detail & Related papers  (2025-09-24T17:58:04Z)

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.