运动感知高斯分组的动态场景时空预测
Space-Time Forecasting of Dynamic Scenes with Motion-aware Gaussian Grouping
把 4D 高斯泼溅从「重建已观测动态」推进到「外推未来」，其运动感知高斯分组与组级优化可作为动态场景表示的结构化先验，供后续做长时预测或动态新视角合成的论文复用。
原文依据 a framework for long-term scene extrapolation built upon the 4D Gaussian Splatting representation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论动态场景预测仍是计算机视觉中的一项基础性挑战，因为有限的观测难以捕捉连贯的物体级运动与长时序演化。本文提出运动分组感知高斯预测（MoGaF），这是一个建立在 4D 高斯泼溅表示之上的长时场景外推框架。MoGaF 引入运动感知高斯分组与组级优化，在刚性与非刚性区域上施加物理一致的运动约束，从而得到空间连贯的动态表示。借助这一结构化时空表示，一个轻量级预测模块预测未来运动，实现真实且时序稳定的场景演化。在合成与真实数据集上的实验表明，MoGaF 在渲染质量、运动合理性与长时预测稳定性上均持续优于现有基线。
英文原文摘要 924 字符
Forecasting dynamic scenes remains a fundamental challenge in computer vision, as limited observations make it difficult to capture coherent object-level motion and long-term temporal evolution.We present Motion Group-aware Gaussian Forecasting (MoGaF), a framework for long-term scene extrapolation built upon the 4D Gaussian Splatting representation.MoGaF introduces motion-aware Gaussian grouping and group-wise optimization to enforce physically consistent motion across both rigid and non-rigid regions, yielding spatially coherent dynamic representations.Leveraging this structured space-time representation, a lightweight forecasting module predicts future motion, enabling realistic and temporally stable scene evolution.Experiments on synthetic and real-world datasets demonstrate that MoGaF consistently outperforms existing baselines in rendering quality, motion plausibility, and long-term forecasting stability.