AI RESEARCH

Space-Time Forecasting of Dynamic Scenes with Motion-aware Gaussian Grouping

arXiv CS.CV

ArXi:2602.21668v2 Announce Type: replace 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