Node-RF: Learning Generalized Continuous Space-Time Scene Dynamics with Neural ODE-based NeRFs
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910051408543744 |
|---|---|
| author | Sarkar, Hiran Kuang, Liming Velikova, Yordanka Busam, Benjamin |
| author_facet | Sarkar, Hiran Kuang, Liming Velikova, Yordanka Busam, Benjamin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_12078 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Node-RF: Learning Generalized Continuous Space-Time Scene Dynamics with Neural ODE-based NeRFs Sarkar, Hiran Kuang, Liming Velikova, Yordanka Busam, Benjamin Computer Vision and Pattern Recognition 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. |
| title | Node-RF: Learning Generalized Continuous Space-Time Scene Dynamics with Neural ODE-based NeRFs |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.12078 |