BézierGS: Dynamic Urban Scene Reconstruction with Bézier Curve Gaussian Splatting
This addresses the problem of large-scale dynamic scene reconstruction for autonomous driving simulators by eliminating dependence on high-precision object annotations.
The paper tackles dynamic urban scene reconstruction for autonomous driving simulators by proposing BézierGS, which uses learnable Bézier curves to model object motion trajectories without relying on object pose annotations. Experiments on Waymo Open Dataset and nuPlan benchmark show it outperforms state-of-the-art methods in reconstruction and novel view synthesis.
The realistic reconstruction of street scenes is critical for developing real-world simulators in autonomous driving. Most existing methods rely on object pose annotations, using these poses to reconstruct dynamic objects and move them during the rendering process. This dependence on high-precision object annotations limits large-scale and extensive scene reconstruction. To address this challenge, we propose Bézier curve Gaussian splatting (BézierGS), which represents the motion trajectories of dynamic objects using learnable Bézier curves. This approach fully leverages the temporal information of dynamic objects and, through learnable curve modeling, automatically corrects pose errors. By introducing additional supervision on dynamic object rendering and inter-curve consistency constraints, we achieve reasonable and accurate separation and reconstruction of scene elements. Extensive experiments on the Waymo Open Dataset and the nuPlan benchmark demonstrate that BézierGS outperforms state-of-the-art alternatives in both dynamic and static scene components reconstruction and novel view synthesis.