Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Chunjiang, Wang, Xiaoyuan, Lin, Qingran, Xiao, Albert, Chen, Haoyu, Wen, Shizheng, Zhang, Hao, Qi, Lu, Yang, Ming-Hsuan, Jeni, Laszlo A., Xu, Min, Zhao, Yizhou
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2603.06022
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910043498086400
author Liu, Chunjiang
Wang, Xiaoyuan
Lin, Qingran
Xiao, Albert
Chen, Haoyu
Wen, Shizheng
Zhang, Hao
Qi, Lu
Yang, Ming-Hsuan
Jeni, Laszlo A.
Xu, Min
Zhao, Yizhou
author_facet Liu, Chunjiang
Wang, Xiaoyuan
Lin, Qingran
Xiao, Albert
Chen, Haoyu
Wen, Shizheng
Zhang, Hao
Qi, Lu
Yang, Ming-Hsuan
Jeni, Laszlo A.
Xu, Min
Zhao, Yizhou
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_06022
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MOSIV: Multi-Object System Identification from Videos
Liu, Chunjiang
Wang, Xiaoyuan
Lin, Qingran
Xiao, Albert
Chen, Haoyu
Wen, Shizheng
Zhang, Hao
Qi, Lu
Yang, Ming-Hsuan
Jeni, Laszlo A.
Xu, Min
Zhao, Yizhou
Computer Vision and Pattern Recognition
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.
title MOSIV: Multi-Object System Identification from Videos
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.06022