M-PhyGs: Multi-Material Object Dynamics from Video

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wada, Norika, Yamashita, Kohei, Kawahara, Ryo, Nishino, Ko
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908720409083904
author Wada, Norika
Yamashita, Kohei
Kawahara, Ryo
Nishino, Ko
author_facet Wada, Norika
Yamashita, Kohei
Kawahara, Ryo
Nishino, Ko
contents Knowledge of the physical material properties governing the dynamics of a real-world object becomes necessary to accurately anticipate its response to unseen interactions. Existing methods for estimating such physical material parameters from visual data assume homogeneous single-material objects, pre-learned dynamics, or simplistic topologies. Real-world objects, however, are often complex in material composition and geometry lying outside the realm of these assumptions. In this paper, we particularly focus on flowers as a representative common object. We introduce Multi-material Physical Gaussians (M-PhyGs) to estimate the material composition and parameters of such multi-material complex natural objects from video. From a short video captured in a natural setting, M-PhyGs jointly segments the object into similar materials and recovers their continuum mechanical parameters while accounting for gravity. M-PhyGs achieves this efficiently with newly introduced cascaded 3D and 2D losses, and by leveraging temporal mini-batching. We introduce a dataset, Phlowers, of people interacting with flowers as a novel platform to evaluate the accuracy of this challenging task of multi-material physical parameter estimation. Experimental results on Phlowers dataset demonstrate the accuracy and effectiveness of M-PhyGs and its components.
format Preprint
id arxiv_https___arxiv_org_abs_2512_16885
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle M-PhyGs: Multi-Material Object Dynamics from Video
Wada, Norika
Yamashita, Kohei
Kawahara, Ryo
Nishino, Ko
Computer Vision and Pattern Recognition
Knowledge of the physical material properties governing the dynamics of a real-world object becomes necessary to accurately anticipate its response to unseen interactions. Existing methods for estimating such physical material parameters from visual data assume homogeneous single-material objects, pre-learned dynamics, or simplistic topologies. Real-world objects, however, are often complex in material composition and geometry lying outside the realm of these assumptions. In this paper, we particularly focus on flowers as a representative common object. We introduce Multi-material Physical Gaussians (M-PhyGs) to estimate the material composition and parameters of such multi-material complex natural objects from video. From a short video captured in a natural setting, M-PhyGs jointly segments the object into similar materials and recovers their continuum mechanical parameters while accounting for gravity. M-PhyGs achieves this efficiently with newly introduced cascaded 3D and 2D losses, and by leveraging temporal mini-batching. We introduce a dataset, Phlowers, of people interacting with flowers as a novel platform to evaluate the accuracy of this challenging task of multi-material physical parameter estimation. Experimental results on Phlowers dataset demonstrate the accuracy and effectiveness of M-PhyGs and its components.
title M-PhyGs: Multi-Material Object Dynamics from Video
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.16885