UrbanGS：用于城市场景重建的语义引导高斯溅射
UrbanGS: Semantic-Guided Gaussian Splatting for Urban Scene Reconstruction
AI总结：
针对城市场景重建中人工标注成本高、动静态元素统一处理降质的问题，提出UrbanGS方法，借助2D语义图区分动静态元素并分别优化，在真实数据集上实现了更优的重建质量与效率。
摘要：
城市场景因几何结构复杂且存在潜在动态物体，其重建工作颇具挑战。基于3D高斯溅射（3D Gaussian Splatting，3DGS）的方法已展现出优异性能，但现有方法通常需引入人工3D标注来优化动态物体建模，由于标注成本高昂，这种做法并不实用。部分方法采用4D高斯溅射（4D Gaussian Splatting，4DGS）表征整个场景，但它们对静态和动态物体不加区分，导致静态元素产生不必要的更新，最终降低重建质量。为解决这些问题，我们提出UrbanGS，该方法利用2D语义图和现有的动态高斯方法从场景中区分静态物体，实现对确定静态元素和潜在动态元素的分别处理。具体而言，对于确定静态区域，我们施加全局一致性约束以防止动态高斯产生意外变化，并引入基于K近邻（K-nearest neighbor，KNN）的正则化来提升低纹理地面的局部连贯性。值得注意的是，对于潜在动态物体，我们通过可学习时间嵌入聚合时序信息，使每个高斯能够建模随时间变化的形变。在真实世界数据集上开展的大量实验表明，我们的方法在重建质量和效率上均优于当前最优方法，能在准确保留静态内容的同时捕捉动态元素。
英文摘要：
Reconstructing urban scenes is challenging due to their complex geometries and the presence of potentially dynamic objects. 3D Gaussian Splatting (3DGS)-based methods have shown strong performance, but existing approaches often incorporate manual 3D annotations to improve dynamic object modeling, which is impractical due to high labeling costs. Some methods leverage 4D Gaussian Splatting (4DGS) to represent the entire scene, but they treat static and dynamic objects uniformly, leading to unnecessary updates for static elements and ultimately degrading reconstruction quality. To address these issues, we propose UrbanGS, which leverages 2D semantic maps and an existing dynamic Gaussian approach to distinguish static objects from the scene, enabling separate processing of definite static and potentially dynamic elements. Specifically, for definite static regions, we enforce global consistency to prevent unintended changes in dynamic Gaussian and introduce a K-nearest neighbor (KNN)-based regularization to improve local coherence on low-textured ground surfaces. Notably, for potentially dynamic objects, we aggregate temporal information using learnable time embeddings, allowing each Gaussian to model deformations over time. Extensive experiments on real-world datasets demonstrate that our approach outperforms state-of-the-art methods in reconstruction quality and efficiency, accurately preserving static content while capturing dynamic elements.
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。
