Node-RF: Learning Generalized Continuous Space-Time Scene Dynamics With Neural ODE-Based NeRFs

MCML Authors

Liming Kuang

→ Group Benjamin Busam
 Photogrammetry and Remote Sensing

Yordanka Velikova

Dr.

→ Group Benjamin Busam
 Photogrammetry and Remote Sensing

Benjamin Busam

Prof. Dr.

Principal Investigator

Photogrammetry and Remote Sensing

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.

inproceedings SKV+26

---

CVPR 2025

IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville, TN, USA, Jun 11-15, 2025. To be published. Preprint available.

---

Authors

H. Sarkar • L. Kuang • Y. Velikova • B. Busam

---

Links

arXiv

---

Research Area

 B1 | Computer Vision