NeuROK: Generative 4D Neural Object Kinematics

• URL: http://arxiv.org/abs/2605.30347v1
• Date: Thu, 28 May 2026 17:59:53 GMT
• Title: NeuROK: Generative 4D Neural Object Kinematics
• Abstract summary: 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.
• Score: 35.76495786203886
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Data-driven approaches have revolutionized 3D vision, enabling transformers to effectively reconstruct and generate static 3D objects. However, generating simulative 4D dynamics -- realistic temporal deformations of static objects under various physical conditions -- remains challenging and often ad hoc, despite its importance in building comprehensive 3D world models. Most existing methods assume a predefined physical model and use system identification to estimate parameters, restricting these methods to specific categories and small-scale datasets. We propose that these restrictions can be overcome by learning a data-driven kinematic state parameterization for object-centric physical systems. Specifically, we learn both a latent space representing all possible states of the object and a decoder that maps any sampled latent to a plausibly deformed shape of the object. We refer to this parameterization as Neural Object Kinematics (NeuROK), and learn a transformer-based encoder-decoder model on a curated large-scale 4D dataset. This formulation and the learned model significantly simplify the generation of simulative dynamics since we only need to consider the dynamics within a low-dimensional latent space from the Lagrangian mechanics' perspective in classical physics. We demonstrate the effectiveness and generality of this neural simulation framework across diverse dynamic object types, showing clear advantages over prior works. Project page: https://chen-geng.com/neurok

Related papers

• ODeform: Learning Continuous 4D Motion for Shape Deformation with Neural ODEs [21.51657616248173]
  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.
  arXiv  Detail & Related papers  (2026-07-22T19:08:31Z)
• 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)
• Instruct-Particulate: Scaling Feed-Forward 3D Object Articulation with Kinematic Control [86.64250947574749]
  Reconstructing articulated 3D objects is important for animation, gaming, and robotic simulations.<n>Recent neural networks can estimate the articulated structure of 3D objects, but their generalization remains limited by the scarcity of annotated data.<n>We introduce Instruct-Particulate, a model that takes a 3D mesh together with a target kinematic specification.
  arXiv  Detail & Related papers  (2026-06-12T17:59:36Z)
• TRACE: Learning 3D Gaussian Physical Dynamics from Multi-view Videos [7.616167860385134]
  We propose a new framework named TRACE to model the motion physics of complex dynamic 3D scenes.<n>By formulating each 3D point as a rigid particle with size and orientation in space, we directly learn a translation rotation dynamics system for each particle.
  arXiv  Detail & Related papers  (2025-08-13T13:43:01Z)
• Particle-Grid Neural Dynamics for Learning Deformable Object Models from RGB-D Videos [28.473117601626956]
  We develop a neural dynamics framework that combines object particles and spatial grids in a hybrid representation.<n>We demonstrate that our model learns the dynamics of diverse objects from sparse-view RGB-D recordings of robot-object interactions.<n>Our approach outperforms state-of-the-art learning-based and physics-based simulators, particularly in scenarios with limited camera views.
  arXiv  Detail & Related papers  (2025-06-18T17:59:38Z)
• DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos [52.46386528202226]
  We introduce the Deformable Gaussian Splats Large Reconstruction Model (DGS-LRM)<n>It is the first feed-forward method predicting deformable 3D Gaussian splats from a monocular posed video of any dynamic scene.<n>It achieves performance on par with state-of-the-art monocular video 3D tracking methods.
  arXiv  Detail & Related papers  (2025-06-11T17:59:58Z)
• Efficient Physics Simulation for 3D Scenes via MLLM-Guided Gaussian Splatting [32.846428862045634]
  We present Sim Anything, a physics-based approach that endows static 3D objects with interactive dynamics.<n>Inspired by human visual reasoning, we propose MLLM-based Physical Property Perception.<n>We also simulate objects in an open-world scene with particles sampled via the Physical-Geometric Adaptive Sampling.
  arXiv  Detail & Related papers  (2024-11-19T12:52:21Z)
• DreamPhysics: Learning Physics-Based 3D Dynamics with Video Diffusion Priors [75.83647027123119]
  We propose to learn the physical properties of a material field with video diffusion priors.<n>We then utilize a physics-based Material-Point-Method simulator to generate 4D content with realistic motions.
  arXiv  Detail & Related papers  (2024-06-03T16:05:25Z)
• 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)
• {\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)
• Secrets of 3D Implicit Object Shape Reconstruction in the Wild [92.5554695397653]
  Reconstructing high-fidelity 3D objects from sparse, partial observation is crucial for various applications in computer vision, robotics, and graphics. Recent neural implicit modeling methods show promising results on synthetic or dense datasets. But, they perform poorly on real-world data that is sparse and noisy. This paper analyzes the root cause of such deficient performance of a popular neural implicit model.
  arXiv  Detail & Related papers  (2021-01-18T03:24:48Z)
• 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.