AI RESEARCH
TRiGS: Temporal Rigid-Body Motion for Scalable 4D Gaussian Splatting
arXiv CS.CV
•
ArXi:2604.00538v1 Announce Type: new Recent 4D Gaussian Splatting (4DGS) methods achieve impressive dynamic scene reconstruction but often rely on piecewise linear velocity approximations and short temporal windows. This disjointed modeling leads to severe temporal fragmentation, forcing primitives to be repeatedly eliminated and regenerated to track complex nonlinear dynamics. This makeshift approximation eliminates the long-term temporal identity of objects and causes an inevitable proliferation of Gaussians, hindering scalability to extended video sequences.