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

arXiv: https://arxiv.org/abs/2511.08310 · HTML: https://mlsanity.com/paper/2511.08310/

## Key facts

- Cited by 4 papers in the map (data through 7 Oct 2026).
- Builds on 27 of its 44 references that are in the map.
- First posted on arXiv 11 Nov 2025.

## Builds on (most cited first, 27 of 27)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [D-NeRF: Neural Radiance Fields for Dynamic Scenes](https://mlsanity.com/paper/2011.13961/) (2020)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [Learning Mesh-Based Simulation with Graph Networks](https://mlsanity.com/paper/2010.03409/) (2020)
- [Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction](https://mlsanity.com/paper/2309.13101/) (2023)
- [Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video](https://mlsanity.com/paper/2012.12247/) (2020)
- [Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids](https://mlsanity.com/paper/1810.01566/) (2018)
- [CAN-PINN: A Fast Physics-Informed Neural Network Based on Coupled-Automatic-Numerical Differentiation Method](https://mlsanity.com/paper/2110.15832/) (2021)
- [Reconstruction and Simulation of Elastic Objects with Spring-Mass 3D Gaussians](https://mlsanity.com/paper/2403.09434/) (2024)
- [PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos](https://mlsanity.com/paper/2503.17973/) (2025)
- [Learning to Manipulate Deformable Objects without Demonstrations](https://mlsanity.com/paper/1910.13439/) (2019)
- [RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Tools](https://mlsanity.com/paper/2306.14447/) (2023)
- [RoboCraft: Learning to See, Simulate, and Shape Elasto-Plastic Objects with Graph Networks](https://mlsanity.com/paper/2205.02909/) (2022)
- [DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic Interactions](https://mlsanity.com/paper/1906.03853/) (2019)
- [Learning Visible Connectivity Dynamics for Cloth Smoothing](https://mlsanity.com/paper/2105.10389/) (2021)
- [ComPhy: Compositional Physical Reasoning of Objects and Events from Videos](https://mlsanity.com/paper/2205.01089/) (2022)
- [Learning Neural Constitutive Laws From Motion Observations for Generalizable PDE Dynamics](https://mlsanity.com/paper/2304.14369/) (2023)
- [PIE-NeRF: Physics-based Interactive Elastodynamics with NeRF](https://mlsanity.com/paper/2311.13099/) (2023)
- [Dynamic 3D Gaussian Tracking for Graph-Based Neural Dynamics Modeling](https://mlsanity.com/paper/2410.18912/) (2024)
- [Context is Everything: Implicit Identification for Dynamics Adaptation](https://mlsanity.com/paper/2203.05549/) (2022)
- [Can Transfer Neuroevolution Tractably Solve Your Differential Equations?](https://mlsanity.com/paper/2101.01998/) (2021)
- [Precise-Physics Driven Text-to-3D Generation](https://mlsanity.com/paper/2403.12438/) (2024)
- [Few-shot NeRF by Adaptive Rendering Loss Regularization](https://mlsanity.com/paper/2410.17839/) (2024)
- [Pushing Rendering Boundaries: Hard Gaussian Splatting](https://mlsanity.com/paper/2412.04826/) (2024)

## Built on by (most cited first, 4 of 4)

- [MatPhys: Learning Material-Aware Physics Parameters for Deformable Object Simulation from Videos](https://mlsanity.com/paper/2605.19386/) (2026)
- [PhysHanDI: Physics-Based Reconstruction of Hand-Deformable Object Interactions](https://mlsanity.com/paper/2605.09538/) (2026)
- [WorldString: Actionable World Representation](https://mlsanity.com/paper/2605.18743/) (2026)
- [MoSA: Motion-constrained Stress Adaptation for Mitigating Real-to-Sim Gap in Continuum Dynamics via Learning Residual Anisotropy](https://mlsanity.com/paper/2605.22597/) (2026)

## Abstract (arXiv)

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.