English

MOSIV: Multi-Object System Identification from Videos

Computer Vision and Pattern Recognition 2026-03-09 v1

Abstract

We introduce the challenging problem of multi-object system identification from videos, for which prior methods are ill-suited due to their focus on single-object scenes or discrete material classification with a fixed set of material prototypes. To address this, we propose MOSIV, a new framework that directly optimizes for continuous, per-object material parameters using a differentiable simulator guided by geometric objectives derived from video. We also present a new synthetic benchmark with contact-rich, multi-object interactions to facilitate evaluation. On this benchmark, MOSIV substantially improves grounding accuracy and long-horizon simulation fidelity over adapted baselines, establishing it as a strong baseline for this new task. Our analysis shows that object-level fine-grained supervision and geometry-aligned objectives are critical for stable optimization in these complex, multi-object settings. The source code and dataset will be released.

Keywords

Cite

@article{arxiv.2603.06022,
  title  = {MOSIV: Multi-Object System Identification from Videos},
  author = {Chunjiang Liu and Xiaoyuan Wang and Qingran Lin and Albert Xiao and Haoyu Chen and Shizheng Wen and Hao Zhang and Lu Qi and Ming-Hsuan Yang and Laszlo A. Jeni and Min Xu and Yizhou Zhao},
  journal= {arXiv preprint arXiv:2603.06022},
  year   = {2026}
}

Comments

ICLR 2026

R2 v1 2026-07-01T11:06:23.184Z