Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

IRIS: A Real-World Benchmark for Inverse Recovery and Identification of Physical Dynamic Systems from Monocular Video

Rasul Khanbayov, Mohamed Rayan Barhdadi, Erchin Serpedin, Hasan Kurban

Abstract

Unsupervised physical parameter estimation from video lacks a common benchmark: existing methods evaluate on non-overlapping synthetic data, the sole real-world dataset is restricted to single-body systems, and no established protocol addresses governing-equation identification. This work introduces IRIS, a high-fidelity benchmark comprising 220 real-world videos captured at 4K resolution and 60\,fps, spanning both single- and multi-body dynamics with independently measured ground-truth parameters and uncertainty estimates. Each dynamical system is recorded under controlled laboratory conditions and paired with its governing equations, enabling principled evaluation. A standardized evaluation protocol is defined encompassing parameter accuracy, identifiability, extrapolation, robustness, and governing-equation selection. Multiple baselines are evaluated, including a multi-step physics loss formulation and four complementary equation-identification strategies (VLM temporal reasoning, describe-then-classify prompting, CNN-based classification, and path-based labelling), establishing reference performance across all IRIS scenarios and exposing systematic failure modes that motivate future research. The dataset, annotations, evaluation toolkit, and all baseline implementations are publicly released.

IRIS: A Real-World Benchmark for Inverse Recovery and Identification of Physical Dynamic Systems from Monocular Video

Abstract

Unsupervised physical parameter estimation from video lacks a common benchmark: existing methods evaluate on non-overlapping synthetic data, the sole real-world dataset is restricted to single-body systems, and no established protocol addresses governing-equation identification. This work introduces IRIS, a high-fidelity benchmark comprising 220 real-world videos captured at 4K resolution and 60\,fps, spanning both single- and multi-body dynamics with independently measured ground-truth parameters and uncertainty estimates. Each dynamical system is recorded under controlled laboratory conditions and paired with its governing equations, enabling principled evaluation. A standardized evaluation protocol is defined encompassing parameter accuracy, identifiability, extrapolation, robustness, and governing-equation selection. Multiple baselines are evaluated, including a multi-step physics loss formulation and four complementary equation-identification strategies (VLM temporal reasoning, describe-then-classify prompting, CNN-based classification, and path-based labelling), establishing reference performance across all IRIS scenarios and exposing systematic failure modes that motivate future research. The dataset, annotations, evaluation toolkit, and all baseline implementations are publicly released.
Paper Structure (60 sections, 4 equations, 1 figure, 17 tables)

This paper contains 60 sections, 4 equations, 1 figure, 17 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Physical Parameter Estimation from Video
  4. Video Benchmarks for Physical Understanding
  5. Vision-Language Models for Physical Reasoning
  6. Governing Equation Discovery
  7. Differentiable Contact and Rigid-Body Simulation
  8. Latent ODE Stabilization
  9. The IRIS Benchmark
  10. Task Definition
  11. Design Principles
  12. Why Real Data?
  13. Physical Phenomena and ODE Bank
  14. Annotations and Ground Truth
  15. Comparison with Existing Benchmarks
  16. ...and 45 more sections

Figures (1)

  • Figure 1: Overview of the IRIS benchmark. Each column corresponds to one of the eight dynamical phenomena; rows show temporally ordered frames sampled from a representative video clip. Left: single-body phenomena, including dropping ball, falling ball, pendulum, and sliding cone. Right: phenomena unique to IRIS, including rotating cone, hitting cones, and two pendulums. The bottom row indicates the physical parameters targeted for estimation. All videos are recorded at 4K resolution and 60 fps under controlled laboratory conditions with independently measured ground-truth parameters.