用连续动态模型预测3D场景未来变化，突破时间窗口限制。
ODE-GS: Latent ODEs for Dynamic Scene Extrapolation with 3D Gaussian Splatting
- 将3D高斯点云轨迹建模为连续潜变量微分方程，摆脱时间戳依赖。
- 在三个基准上实现19.8%的性能提升，显著优于现有方法。
- 适合需要长期动态预测的场景建模任务，如自动驾驶与机器人导航。
我们提出ODE-GS，一种将3D高斯溅射与潜在神经常微分方程（ODE）结合的新方法，实现动态3D场景的未来外推。不同于依赖时间条件形变网络且仅限于固定时间窗内插值的现有方法，ODE-GS通过将高斯参数轨迹建模为连续时间潜态动态，消除了时间戳依赖。该方法首先学习一个插值模型以生成观测窗口内的准确高斯轨迹，随后训练Transformer编码器将历史轨迹聚合为潜状态，并通过神经ODE演化该状态；最后通过数值积分生成平滑、物理合理的未来高斯轨迹，支持任意未来时间点的渲染。在D-NeRF、NVFi和HyperNeRF基准上，ODE-GS达到领先外推性能，相比顶尖基线指标提升19.8%，验证了其对3D场景动态的精确表征与预测能力。
原文摘要 · Abstract (English)
We introduce ODE-GS, a novel approach that integrates 3D Gaussian Splatting with latent neural ordinary differential equations (ODEs) to enable future extrapolation of dynamic 3D scenes. Unlike existing dynamic scene reconstruction methods, which rely on time-conditioned deformation networks and are limited to interpolation within a fixed time window, ODE-GS eliminates timestamp dependency by modeling Gaussian parameter trajectories as continuous-time latent dynamics. Our approach first learns an interpolation model to generate accurate Gaussian trajectories within the observed window, then trains a Transformer encoder to aggregate past trajectories into a latent state evolved via a neural ODE. Finally, numerical integration produces smooth, physically plausible future Gaussian trajectories, enabling rendering at arbitrary future timestamps. On the D-NeRF, NVFi, and HyperNeRF benchmarks, ODE-GS achieves state-of-the-art extrapolation performance, improving metrics by 19.8% compared to leading baselines, demonstrating its ability to accurately represent and predict 3D scene dynamics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。