ICLR2025
SplineGS: Learning Smooth Trajectories in Gaussian Splatting for Dynamic Scene Reconstruction
Jihwan Yoon, Sangbeom Han, Jaeseok Oh, Minsik Lee
Abstract
Jumping jacks (b) Stand up (c) NURBS Figure 1: We propose SplineGS, which represents the trajectories in Gaussian splatting using nonuniform rational B-spline (NURBS) to reconstruct dynamic scenes. The learned trajectories are shown with rendering results in (a) and (b). (c) shows an example of a trajectory based on NURBS.