B\'ezierGS: Dynamic Urban Scene Reconstruction with B\'ezier Curve Gaussian Splatting

TL;DR

BézierGS is a novel method for reconstructing dynamic urban scenes that uses learnable Bézier curves to model object trajectories, reducing reliance on precise annotations and improving reconstruction accuracy.

Contribution

The paper introduces BézierGS, a new approach leveraging learnable Bézier curves for dynamic scene reconstruction, enabling automatic pose correction and improved scene element separation.

Findings

Outperforms state-of-the-art methods in scene reconstruction

Accurately models dynamic object trajectories

Enhances novel view synthesis quality

Abstract

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 B\'ezier curve Gaussian splatting (B\'ezierGS), which represents the motion trajectories of dynamic objects using learnable B\'ezier 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 B\'ezierGS outperforms state-of-the-art alternatives in both dynamic and static scene components reconstruction and novel view synthesis.