Node-RF: Learning Generalized Continuous Space-Time Scene Dynamics with Neural ODE-based NeRFs
This addresses the challenge of generalizing scene dynamics for computer vision applications, representing a novel method for a known bottleneck rather than incremental.
The paper tackles the problem of predicting scene dynamics from visual observations, which existing methods fail to extrapolate far beyond training sequences, by proposing Node-RF, a method that integrates Neural ODEs with dynamic NeRFs to enable continuous-time, spatiotemporal representations that generalize beyond observed trajectories at constant memory cost.
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.