SparseStreet: 用于实时街景模拟的稀疏高斯泼溅
SparseStreet: Sparse Gaussian Splatting for Real-Time Street Scene Simulation
AI总结：
针对街景重建中高斯原语冗余问题，提出节点可学习剪枝与背景压缩框架，实现高达80%压缩比且质量损失极小。
摘要：
尽管3D高斯泼溅在街景重建中显示出有希望的结果，现有方法需要大量高斯原语来捕捉细节，导致存储成本过高和渲染速度缓慢。我们观察到动态对象（如车辆和行人）需要高保真表示以保持时间一致性，而静态背景区域通常包含大量冗余。受此启发，我们提出SparseStreet，一种专为街景设计的通用压缩框架。首先，我们引入基于节点的可学习剪枝策略，系统性地移除低贡献高斯原语，同时保留视觉关键区域。其次，在场景表示稳定后，我们应用背景压缩，进一步减少静态区域中的冗余。我们的方法有效保留了动态对象的几何和外观，同时显著减少了高斯原语的总数。在Waymo和nuScenes上的大量实验表明，SparseStreet实现了高达80%的压缩比，且质量退化极小，实现了资源高效、高保真的动态场景重建。项目网站：此 https URL。
英文摘要：
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/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
