用运动感知分组的高斯表示，实现动态场景长期稳定预测
Space-Time Forecasting of Dynamic Scenes with Motion-aware Gaussian Grouping
- 通过运动感知分组和分组优化，建模刚性与非刚性区域一致运动
- 在合成与真实数据集上，长期预测稳定性与运动合理性显著优于基线
- 适合需要精准动态演化建模的自动驾驶与视频生成场景
动态场景预测仍是计算机视觉中的基础挑战，受限观测难以捕捉一致的物体级运动与长期时序演变。我们提出运动感知高斯分组（MoGaF）框架，基于4D高斯点阵表示实现长期场景外推。MoGaF引入运动感知高斯分组与分组优化机制，确保刚性与非刚性区域的物理一致性运动，生成空间一致的动态表征。借助此结构化时空表示，轻量级预测模块可生成未来运动，实现逼真且时间稳定的场景演化。在合成与真实世界数据集上的实验表明，MoGaF在渲染质量、运动合理性及长期预测稳定性方面持续优于现有基线。
原文摘要 · Abstract (English)
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. Our project page is available at https://slime0519.github.io/mogaf
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。