Dynamic Street-Scene Reconstruction with Semantic Priors and Temporal Constraints

Dynamic street-scene reconstruction from sparse viewpoints over long temporal spans is challenged by temporal instability, ghosting near occlusions, and background drift. This paper presents SPT-Gauss, a Gaussian-splatting framework that improves dynamic reconstruction without object-level annotations by combining dense semantic priors with lightweight, parameter-level temporal regularization. SPT-Gauss distills per-pixel semantic features from a frozen 2D foundation model into 4D Gaussian primitives, estimates static and dynamic regions via a dual-evidence motion mask, and regularizes temporal parameters through a semantic-guided velocity constraint and a static-lifetime prior to suppress spurious background motion. Experiments on the Waymo Open Dataset and KITTI show consistent improvements over representative baselines in both 4D reconstruction and novel-view synthesis, with reduced temporal artifacts and improved fidelity in motion-challenging regions.