FreeForm: Reduced-Order Deformable Simulation from Particle-Based Skinning Eigenmodes

Hugging Face Daily Papers Papers

Summary

This paper presents FreeForm, a reduced-order simulation method for deformable hyperelastic objects using a Reproducing Kernel Particle Method (RKPM) that achieves 40x faster training and lower error than neural field approaches.

We present a novel formulation for mesh-free, reduced-order simulation of deformable hyperelastic objects. Existing work in reduced-order elastodynamic simulation represents the input geometry by either meshes, which can be difficult to obtain due to challenges in scanning and triangulating complex shapes, or by neural fields that require per-shape optimization. We propose to adopt a Reproducing Kernel Particle Method (RKPM) representation, which enables the construction of reduced-order skinning weights by solving a generalized eigensystem on the Hessian matrix of the elastic energy. We demonstrate that this formulation not only leads to a 40x training speedup compared with the per-shape optimization of neural fields, but also achieves lower simulation error when evaluated against the converged results of finite element method. We show our simulation results on a wide variety of objects in different representations including meshes and Gaussian splats, as well as the application of our method in the downstream task of robot simulation.
Original Article
View Cached Full Text

Cached at: 06/02/26, 07:33 PM

Paper page - FreeForm: Reduced-Order Deformable Simulation from Particle-Based Skinning Eigenmodes

Source: https://huggingface.co/papers/2605.29318

Abstract

Reduced-order simulation of deformable hyperelastic objects using Reproducing Kernel Particle Method achieves faster training and lower error compared to neural field approaches while supporting various geometric representations.

We present a novel formulation formesh-free,reduced-order simulationof deformable hyperelastic objects. Existing work in reduced-order elastodynamic simulation represents the input geometry by either meshes, which can be difficult to obtain due to challenges in scanning and triangulating complex shapes, or byneural fieldsthat require per-shape optimization. We propose to adopt aReproducing Kernel Particle Method(RKPM) representation, which enables the construction of reduced-order skinning weights by solving ageneralized eigensystemon theHessian matrixof theelastic energy. We demonstrate that this formulation not only leads to a 40x training speedup compared with the per-shape optimization ofneural fields, but also achieves lower simulation error when evaluated against the converged results offinite element method. We show our simulation results on a wide variety of objects in different representations including meshes and Gaussian splats, as well as the application of our method in the downstream task ofrobot simulation.

View arXiv pageView PDFGitHub5.1kAdd to collection

Get this paper in your agent:

hf papers read 2605\.29318

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.29318 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.29318 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.29318 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

NeuROK: Generative 4D Neural Object Kinematics

Hugging Face Daily Papers

This paper introduces NeuROK, a data-driven approach for generative 4D neural object kinematics that learns a latent space and transformer-based encoder-decoder to simulate realistic temporal deformations of static objects under various physical conditions, overcoming limitations of predefined physical models.

RigidFormer: Learning Rigid Dynamics using Transformers

Hugging Face Daily Papers

RigidFormer is a new mesh-free, object-centric Transformer model that learns rigid dynamics from point clouds, outperforming mesh-based baselines in speed and scalability for multi-object contact dynamics.

FFJORD: Free-form continuous dynamics for scalable reversible generative models

OpenAI Blog

FFJORD introduces a scalable reversible generative model using continuous dynamics and Hutchinson's trace estimator to enable unbiased log-density estimation without architectural constraints. The method achieves state-of-the-art results on density estimation and image generation while maintaining efficient sampling.

Language Modeling with Hyperspherical Flows

arXiv cs.LG

This paper introduces S-FLM, a novel flow-based language model that operates in a hyperspherical latent space to address the computational costs and semantic limitations of existing discrete diffusion and continuous flow models.