用稀疏化技术压缩街景3D高斯点云，提升渲染速度。
SparseStreet: Sparse Gaussian Splatting for Real-Time Street Scene Simulation
- 按贡献度动态删减高斯点，保留关键区域。
- 静态背景进一步压缩，最高达80%体积减少。
- 适合实时街景重建，兼顾质量与效率。
尽管3D高斯点阵在街景重建中表现优异，但现有方法需大量高斯基元来捕捉细节，导致存储成本高昂且渲染缓慢。我们观察到动态物体（如车辆和行人）需高保真表示以维持时序一致性，而静态背景则存在显著冗余。为此，提出专为街景设计的SparseStreet压缩框架：首先引入基于节点的可学习剪枝策略，系统性移除低贡献高斯基元，同时保留视觉关键区域；其次，在场景表示稳定后对背景进行压缩，进一步消除静态区域冗余。该方法有效保持动态物体的几何与外观，显著减少高斯基元总数。在Waymo和nuScenes数据集上的实验表明，SparseStreet可实现高达80%的压缩比，且质量损失极小，支持资源高效、高保真的动态场景重建。
原文摘要 · Abstract (English)
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/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。