NEXUS framework models physically consistent 3D object dynamics

Researchers have introduced NEXUS, a novel neural energy-field framework designed to model physically consistent contact-rich 3D object dynamics. Unlike previous methods that often model isolated physical effects, NEXUS composes conservative and non-conservative dynamics by representing objects as structural graphs and constructing dynamic contact graphs. The framework formulates motion through scalar energy and dissipation terms, inspired by Hamiltonian Neural Networks, allowing for additive composition of conservative effects like gravity and elastic deformation, and learned modeling of non-conservative effects such as damping and impact-induced energy loss. NEXUS has demonstrated improved long-horizon accuracy on trajectory benchmarks and shows promise for guiding contact-rich video generation with enhanced physical plausibility and visual quality. AI

IMPACT Introduces a new framework for physically consistent 3D object dynamics, potentially improving realism in physics-grounded video generation.

RANK_REASON The cluster contains a research paper detailing a new methodology for modeling 3D object dynamics. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• arXiv
• CatalyzeX Code Finder for Papers
• Connected Papers
• CORE Recommender
• DagsHub
• Gotit.pub
• Hamiltonian Neural Networks
• Hugging Face
• Litmaps
• NEXUS
• ScienceCast
• scite Smart Citations

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →