arXiv cs.AI· Qizhen Ying, Guangming Wang, Yangchen Pan, Victor Adrian Prisacariu, Brian Sheil, Yixiong Jing·· 3 小时前AI 评分38
NEXUS：面向物理一致接触密集型 3D 物体动力学的神经能量场框架
NEXUS: Neural Energy Fields for Physically Consistent Contact-Rich 3D Object Dynamics
AI 导读
arXiv 论文提出 NEXUS，一个用于接触密集型 3D 物体动力学的神经能量场框架。它受 Hamiltonian Neural Networks 启发，通过标量能量项和学习的 Rayleigh 式耗散项来建模运动，保守效应（重力、弹性形变）与非保守效应（阻尼、冲击能量损失）可叠加组合。
正文 · 原文
Abstract:Physics-grounded video generation requires controllable 3D object dynamics that remain physically consistent under contact, deformation, and external forcing. Existing trajectory-based methods often model isolated physical effects, making it difficult to compose conservative and non-conservative dynamics in contact-rich 3D scenes. We present NEXUS, a neural energy-field framework for contact-rich 3D object dynamics. NEXUS represents each object as a structural graph and constructs dynamic object-object and object-environment contact graphs. Inspired by Hamiltonian Neural Networks, NEXUS formulates motion through scalar energy and dissipation terms rather than directly predicting states or accelerations. Conservative effects, including gravity and elastic deformation, are composed as additive energy terms, while non-conservative effects such as damping and impact-induced energy loss are modeled with learned Rayleigh-style dissipation. Forces are derived by differentiating the energy and dissipation functions and rolled out with a multi-substep semi-implicit integrator. Across controlled trajectory benchmarks, NEXUS improves long-horizon accuracy over representative learned and physics-structured dynamics baselines under varying mechanical properties and physical-effect compositions. We further show that NEXUS trajectories provide effective guidance for contact-rich video generation, improving physical plausibility while maintaining competitive visual quality.
| Comments: | 18 pages, 4 figures, 6 tables. Preprint |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.15015 [cs.CV] |
| (or arXiv:2606.15015v3 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2606.15015 arXiv-issued DOI via DataCite |
Submission history
From: Qizhen Ying [view email]
[v1]
Fri, 12 Jun 2026 23:24:41 UTC (18,745 KB)
[v2]
Thu, 18 Jun 2026 06:53:24 UTC (18,745 KB)
[v3]
Wed, 11 Nov 2026 17:23:29 UTC (33,020 KB)
来源：arXiv cs.AI · arxiv.org