Node-RF：基于神经常微分方程 NeRF 学习泛化的连续时空场景动态
Node-RF: Learning Generalized Continuous Space-Time Scene Dynamics with Neural ODE-based NeRFs
把 NODE 的连续时间状态演化嵌入动态 NeRF 的隐式表示中，用 ODE 求解器在特征空间做长程外推，为动态场景建模提供了一种常数显存、可跨观测边界预测未来视角与状态的思路，可直接迁移到动态新视角合成与时空预测任务。
原文依据 integrating Neural Ordinary Differential Equations (NODEs) with dynamic Neural Radiance Fields (NeRFs)
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从视觉观测中预测场景动态具有挑战性。现有方法仅在观测边界内捕捉动态，无法外推到远超训练序列的范围。Node-RF（基于神经常微分方程的 NeRF）通过将神经常微分方程（NODE）与动态神经辐射场（NeRF）相结合，克服了这一局限，实现了连续时间的时空表示，能够在常数显存开销下泛化到观测轨迹之外。Node-RF 从视觉输入中学习一个随时间经由 ODE 求解器演化的隐式场景状态，通过微分计算传播特征嵌入。基于 NeRF 的渲染器解释计算得到的嵌入，以合成任意视角用于长程外推。在具有共享动态的多个运动序列上进行训练，使其能够泛化到未见条件。实验表明，Node-RF 无需显式模型即可刻画抽象的系统行为，以识别用于未来预测的关键点。代码将公开。
英文原文摘要 1063 字符
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. Our code will be made publicly available.