ODeform: Learning Continuous 4D Motion for Shape Deformation with Neural ODEs

• URL: http://arxiv.org/abs/2607.20670v1
• Date: Wed, 22 Jul 2026 19:08:31 GMT
• Title: ODeform: Learning Continuous 4D Motion for Shape Deformation with Neural ODEs
• Abstract summary: We present ODeform, a novel extension of Neural Ordinary Differential Equations to continuous 4D dynamics of deformable objects in 3D space.<n>Our method transforms 3D point clouds and physical conditions (like material properties) into a unified latent space.<n>By solving the resulting ordinary differential equations over time, we model deformations as continuous flows within this learned embedding, eliminating the need for discrete time steps while maintaining computational efficiency.
• Score: 21.51657616248173
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Modeling continuous object deformation is important for many computer vision and robotics tasks, such as manipulation and simulation. Existing approaches rely on learning-based methods or physics simulators to model shape deformations. However, these approaches either use discrete time steps or are too computationally intensive for real-time applications. We present ODeform, a novel extension of Neural Ordinary Differential Equations to continuous 4D dynamics of deformable objects in 3D space. Our method transforms 3D point clouds and physical conditions (like material properties) into a unified latent space. By solving the resulting ordinary differential equations over time, we model deformations as continuous flows within this learned embedding, eliminating the need for discrete time steps while maintaining computational efficiency. We evaluate our approach on unseen physical parameter configurations, showing improved motion prediction accuracy over baseline methods. Our experiments further demonstrate a successful transfer to real 3D captured objects with novel shapes, along with effective interpolation and extrapolation of the learned dynamics. Our code and data will be made publicly available.

Related papers

• PhysiFormer: Learning to Simulate Mechanics in World Space [56.16644631495]
  We present PhysiFormer, a diffusion transformer for physically-plausible 3D object motion.<n>It represents objects as 3D meshes expressed in world coordinates.<n>It substantially outperforms autoregressive baselines in trajectory accuracy, rigidity preservation, and momentum-based physical consistency.
  arXiv  Detail & Related papers  (2026-06-25T17:59:00Z)
• Learning Neural Deformation Representation for 4D Dynamic Shape Generation [18.39851711911021]
  We focus on generating 4D dynamic shapes with an emphasis on both generation quality and efficiency.<n>We propose a new neural deformation representation and combine it with conditional neural signed distance fields to design a 4D representation architecture.<n>The proposed deformation representation, which works by predicting skinning weights and rigid transformations for multiple parts, also has advantages over the deformation modules of existing 4D representations.
  arXiv  Detail & Related papers  (2026-05-31T05:25:11Z)
• NeuROK: Generative 4D Neural Object Kinematics [35.76495786203886]
  We learn a data-driven kinematic state parameterization for object-centric physical systems.<n>We learn a transformer-based encoder-decoder model on a curated large-scale 4D dataset.
  arXiv  Detail & Related papers  (2026-05-28T17:59:53Z)
• D-Garment: Physics-Conditioned Latent Diffusion for Dynamic Garment Deformations [9.991827725035373]
  Garment dynamics influence geometric details such as wrinkling patterns, which depend on physical input including the wearer's body shape and motion, as well as cloth material features.<n>We propose here a learning-based approach trained on data generated with a physics-based simulator.
  arXiv  Detail & Related papers  (2025-04-04T14:18:06Z)
• Equivariant Graph Neural Operator for Modeling 3D Dynamics [148.98826858078556]
  We propose Equivariant Graph Neural Operator (EGNO) to directly models dynamics as trajectories instead of just next-step prediction. EGNO explicitly learns the temporal evolution of 3D dynamics where we formulate the dynamics as a function over time and learn neural operators to approximate it. Comprehensive experiments in multiple domains, including particle simulations, human motion capture, and molecular dynamics, demonstrate the significantly superior performance of EGNO against existing methods.
  arXiv  Detail & Related papers  (2024-01-19T21:50:32Z)
• MoDA: Modeling Deformable 3D Objects from Casual Videos [84.29654142118018]
  We propose neural dual quaternion blend skinning (NeuDBS) to achieve 3D point deformation without skin-collapsing artifacts. In the endeavor to register 2D pixels across different frames, we establish a correspondence between canonical feature embeddings that encodes 3D points within the canonical space. Our approach can reconstruct 3D models for humans and animals with better qualitative and quantitative performance than state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-04-17T13:49:04Z)
• SNUG: Self-Supervised Neural Dynamic Garments [14.83072352654608]
  We present a self-supervised method to learn dynamic 3D deformations of garments worn by parametric human bodies. This allows us to learn models for interactive garments, including dynamic deformations and fine wrinkles, with two orders of magnitude speed up in training time.
  arXiv  Detail & Related papers  (2022-04-05T13:50:21Z)
• {\phi}-SfT: Shape-from-Template with a Physics-Based Deformation Model [69.27632025495512]
  Shape-from-Template (SfT) methods estimate 3D surface deformations from a single monocular RGB camera. This paper proposes a new SfT approach explaining 2D observations through physical simulations.
  arXiv  Detail & Related papers  (2022-03-22T17:59:57Z)
• ACID: Action-Conditional Implicit Visual Dynamics for Deformable Object Manipulation [135.10594078615952]
  We introduce ACID, an action-conditional visual dynamics model for volumetric deformable objects. A benchmark contains over 17,000 action trajectories with six types of plush toys and 78 variants. Our model achieves the best performance in geometry, correspondence, and dynamics predictions.
  arXiv  Detail & Related papers  (2022-03-14T04:56:55Z)
• Identity-Disentangled Neural Deformation Model for Dynamic Meshes [8.826835863410109]
  We learn a neural deformation model that disentangles identity-induced shape variations from pose-dependent deformations using implicit neural functions. We propose two methods to integrate global pose alignment with our neural deformation model. Our method also outperforms traditional skeleton-driven models in reconstructing surface details such as palm prints or tendons without limitations from a fixed template.
  arXiv  Detail & Related papers  (2021-09-30T17:43:06Z)
• gradSim: Differentiable simulation for system identification and visuomotor control [66.37288629125996]
  We present gradSim, a framework that overcomes the dependence on 3D supervision by leveraging differentiable multiphysics simulation and differentiable rendering. Our unified graph enables learning in challenging visuomotor control tasks, without relying on state-based (3D) supervision.
  arXiv  Detail & Related papers  (2021-04-06T16:32:01Z)
• Predicting the Physical Dynamics of Unseen 3D Objects [65.49291702488436]
  We focus on predicting the dynamics of 3D objects on a plane that have just been subjected to an impulsive force. Our approach can generalize to object shapes and initial conditions that were unseen during training. Our model can support training with data from both a physics engine or the real world.
  arXiv  Detail & Related papers  (2020-01-16T06:27:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.