SparseStreet: Sparse Gaussian Splatting for Real-Time Street Scene Simulation
2026-06-02 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors introduce SparseStreet, a method to make 3D models of street scenes smaller and faster by removing unimportant parts. They noticed that moving things like cars need detailed models, but the background can be simplified since it doesn't change much. Their approach first learns which parts can be pruned without losing important details, then compresses the background to reduce redundancy. Tests on popular datasets show that their method cuts down the model size by up to 80% while keeping quality high.
3D Gaussian Splattingstreet scene reconstructioncompressionGaussian primitivesdynamic objectsstatic backgroundpruningtemporal consistencyWaymo datasetnuScenes dataset
Authors
Qingpo Wuwu, Xiaobao Wei, Peng Chen, Nan Huang, Zhongyu Zhao, Hao Wang, Ming Lu, Ningning Ma, Shanghang Zhang
Abstract
While 3D Gaussian Splatting has shown promising results in street scene reconstruction, existing methods require massive numbers of Gaussian primitives to capture fine details, leading to prohibitive storage costs and slow rendering speeds. We observe that dynamic objects (e.g., vehicles and pedestrians) demand high-fidelity representations to maintain temporal consistency, while static background regions often contain substantial redundancy. Motivated by this, we propose SparseStreet, a general compression framework specifically designed for street scenes. First, we introduce a node-based learnable pruning strategy that systematically removes low-contributing Gaussian primitives while preserving visually critical regions. Second, after the scene representation stabilizes, we apply background compression, further reducing redundancy in static regions. Our method effectively preserves the geometry and appearance of dynamic objects while significantly reducing the total number of Gaussian primitives. Extensive experiments on the Waymo and nuScenes demonstrate that SparseStreet achieves up to 80% compression ratio with minimal quality degradation, enabling resource-efficient, high-fidelity dynamic scene reconstruction. Project website: https://sparsestreet.github.io/.