Node-RF: Learning Generalized Continuous Space-Time Scene Dynamics with Neural ODE-based NeRFs

TL;DR

Node-RF combines Neural ODEs with NeRFs to model continuous spatiotemporal scene dynamics, enabling long-range extrapolation from visual data and generalizing beyond observed trajectories.

Contribution

This work introduces Node-RF, a novel framework integrating Neural ODEs with NeRFs for continuous-time scene dynamics modeling, surpassing limitations of existing methods.

Findings

Enables long-range scene extrapolation from visual observations

Generalizes to unseen motion conditions with shared dynamics

Accurately characterizes system behavior without explicit models

Abstract

Predicting scene dynamics from visual observations is challenging. Existing methods capture dynamics only within observed boundaries failing to extrapolate far beyond the training sequence. Node-RF (Neural ODE-based NeRF) overcomes this limitation by integrating Neural Ordinary Differential Equations (NODEs) with dynamic Neural Radiance Fields (NeRFs), enabling a continuous-time, spatiotemporal representation that generalizes beyond observed trajectories at constant memory cost. From visual input, Node-RF learns an implicit scene state that evolves over time via an ODE solver, propagating feature embeddings via differential calculus. A NeRF-based renderer interprets calculated embeddings to synthesize arbitrary views for long-range extrapolation. Training on multiple motion sequences with shared dynamics allows for generalization to unseen conditions. Our experiments demonstrate that Node-RF can characterize abstract system behavior without explicit model to identify critical points for future predictions.