Integrates Neural ODEs with NeRFs to enable continuous-time scene dynamics that can extrapolate far beyond the original training sequence.
arXiv · March 13, 2026 · 2603.12078
Why it matters
Traditional dynamic NeRFs are bounded by their training windows; this approach allows for long-range future prediction of scene movement and system behavior, which is critical for robotics and predictive simulation.
From the 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 inpu