NeuSpring: Neural Spring Fields for Reconstruction and Simulation of Deformable Objects from Videos

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Qingshan, Liu, Jiao, Yu, Shangshu, Wang, Yuxuan, Zhou, Yuan, Zhou, Junbao, Cui, Jiequan, Ong, Yew-Soon, Zhang, Hanwang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915612017557504
author Xu, Qingshan
Liu, Jiao
Yu, Shangshu
Wang, Yuxuan
Zhou, Yuan
Zhou, Junbao
Cui, Jiequan
Ong, Yew-Soon
Zhang, Hanwang
author_facet Xu, Qingshan
Liu, Jiao
Yu, Shangshu
Wang, Yuxuan
Zhou, Yuan
Zhou, Junbao
Cui, Jiequan
Ong, Yew-Soon
Zhang, Hanwang
contents In this paper, we aim to create physical digital twins of deformable objects under interaction. Existing methods focus more on the physical learning of current state modeling, but generalize worse to future prediction. This is because existing methods ignore the intrinsic physical properties of deformable objects, resulting in the limited physical learning in the current state modeling. To address this, we present NeuSpring, a neural spring field for the reconstruction and simulation of deformable objects from videos. Built upon spring-mass models for realistic physical simulation, our method consists of two major innovations: 1) a piecewise topology solution that efficiently models multi-region spring connection topologies using zero-order optimization, which considers the material heterogeneity of real-world objects. 2) a neural spring field that represents spring physical properties across different frames using a canonical coordinate-based neural network, which effectively leverages the spatial associativity of springs for physical learning. Experiments on real-world datasets demonstrate that our NeuSping achieves superior reconstruction and simulation performance for current state modeling and future prediction, with Chamfer distance improved by 20% and 25%, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2511_08310
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NeuSpring: Neural Spring Fields for Reconstruction and Simulation of Deformable Objects from Videos
Xu, Qingshan
Liu, Jiao
Yu, Shangshu
Wang, Yuxuan
Zhou, Yuan
Zhou, Junbao
Cui, Jiequan
Ong, Yew-Soon
Zhang, Hanwang
Computer Vision and Pattern Recognition
In this paper, we aim to create physical digital twins of deformable objects under interaction. Existing methods focus more on the physical learning of current state modeling, but generalize worse to future prediction. This is because existing methods ignore the intrinsic physical properties of deformable objects, resulting in the limited physical learning in the current state modeling. To address this, we present NeuSpring, a neural spring field for the reconstruction and simulation of deformable objects from videos. Built upon spring-mass models for realistic physical simulation, our method consists of two major innovations: 1) a piecewise topology solution that efficiently models multi-region spring connection topologies using zero-order optimization, which considers the material heterogeneity of real-world objects. 2) a neural spring field that represents spring physical properties across different frames using a canonical coordinate-based neural network, which effectively leverages the spatial associativity of springs for physical learning. Experiments on real-world datasets demonstrate that our NeuSping achieves superior reconstruction and simulation performance for current state modeling and future prediction, with Chamfer distance improved by 20% and 25%, respectively.
title NeuSpring: Neural Spring Fields for Reconstruction and Simulation of Deformable Objects from Videos
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.08310