← Back to all news
arXiv Computer Vision By Varun Varma Thozhiyoor, Shivam Tripathi, Venkatesh Babu Radhakrishnan, Anand Bhattad

Principia: Relational Physics Tests for Video Models

Read the original on arXiv Computer Vision →

Principia is a new benchmark that tests video models on Newtonian physics by evaluating relational consistency between paired objects, independent of calibration. It covers eight phenomena—gravity, restitution, friction, rotational inertia, projectile motion, momentum, pendulum, and mass‑spring oscillation—across translational, rotational, collisional, and oscillatory dynamics using real‑world scenes. The benchmark introduces a calibration‑independent consistency score and shows that current state‑of‑the‑art video generators perform poorly on it, with the best vision‑language model achieving only 67% accuracy on detecting physics violations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Oct 2

PhysicsLENS: Diagnosing Physical Property Blindness in Video Generation Models

PhysicsLENS is a new dataset and benchmark designed to evaluate how well video generation models capture physical properties relevant to robotics. It consists of matched scenario pairs that share the same conditioning frame and task but differ in underlying physics, and it covers seven physical domains such as collision, gravity, and friction. The benchmark includes over 400 human-annotated labels from four video generation models, revealing that many plausible-looking videos still ignore the specified physical property.

By Isaiah Milkey, Som Sagar, Aditya Taparia, Xinyuan Liu, Jiqing Wen, Ransalu Senanayake
diffusionroboticsbenchmarks
More like this →
arXiv Computer Vision
Sep 18

SnapPhysics: A Physics-Aware Scene Graph from a Single View for Interactive Mixed Reality Scenes

SnapPhysics is a training‑free framework that reconstructs 3D objects and estimates their physical properties—mass, friction, and center of gravity—from a single image. It combines instance‑level 3D reconstruction with a physics‑aware scene graph to provide geometric grounding and inter‑object relationships for vision‑language model reasoning. Experiments on 3D‑FRONT and real captured scenes show significant improvements over existing methods, enabling physically interactive mixed reality experiences without manual tuning.

By Suji Kang, Seok-Young Kim, Young Bin Kim, Taewook Ha, Dieter Schmalstieg, Shohei Mori, Woontack Woo
llmsmultimodalsafety
More like this →
arXiv Computer Vision
4d ago

GeoFlip: Benchmarking Geometry-Sensitive Physics in Video Generation

GeoFlip is a new benchmark for video generation models that tests their ability to produce physically correct outcomes when the initial geometry of a scene is altered. The benchmark presents 482 pairs of scenes with controlled changes in extent, placement, and mechanism configuration, and evaluates models on event correctness, structural integrity, and similarity to reference videos. Across 16 evaluated models, the best event correctness averaged only 27.98%, highlighting significant gaps in geometry‑sensitive physical reasoning.

By Yuqi Li, Junming Liu, Bowen Hu, Ruize Niu, Huiran Duan, Yingli Tian, Hao Wu
diffusionbenchmarks
More like this →