发表机构
Aerospace Information Research Institute, Chinese Academy of Sciences; University of Chinese Academy of Sciences（中国科学院空天信息创新研究院; 中国科学院大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
STARS-GS是一种面向大规模航空表面重建的结构感知3DGS框架，通过结构感知场景划分、邻域感知高斯组织和自适应表面正则化，在基准测试中相对第二名提升9.1%，平均F1分数达0.698，性能优于现有高斯方法。
AI 中文摘要
从航空影像进行大规模三维表面重建是地理空间制图和城市建模的基础。三维高斯溅射（3DGS）的最新进展已在该任务中展现出巨大潜力，但现有方法在大规模复杂场景中仍面临三大挑战：场景划分可能将连续场景元素拆分至独立优化的子区域；几何约束主要聚焦于单个高斯的属性，却忽略了它们的局部组织；均匀正则化难以适配异构几何结构。为解决这些问题，我们提出STARS-GS，一种用于大规模表面重建的结构感知3DGS框架。首先，我们引入结构感知场景划分策略，该策略在划分过程中更好地保留连续场景结构，并通过边界细化减少跨区域几何不一致性与拼接伪影。其次，我们开发邻域感知高斯组织，将几何约束从单个基元扩展至其邻域组织，促使高斯更好地贴合局部表面几何。第三，我们引入自适应表面正则化，根据局部几何特性调整正则化强度，在结构化区域促进几何一致性，同时在非结构化区域保留合理的变化。在大规模航空摄影测量基准上的大量实验表明，STARS-GS在表面重建中始终优于所评估的基于高斯的方法，它将平均F1分数从排名第二的方法的0.640提升至0.698，对应相对提升约9.1%，证明其在几何精度和表面完整性方面的有效改进。
英文摘要
Large-scale 3D surface reconstruction from aerial imagery is fundamental to geospatial mapping and urban modeling. Recent advances in 3D Gaussian Splatting (3DGS) have demonstrated considerable potential for this task. However, existing methods still face three major challenges in large and complex scenes: scene partitioning may split continuous scene elements across independently optimized sub-regions; geometric constraints mainly focus on the attributes of individual Gaussians while overlooking their local organization; and uniform regularization struggles to accommodate heterogeneous geometric structures. To address these issues, we propose STARS-GS, a structure-aware 3DGS framework for large-scale surface reconstruction. First, we introduce a structure-aware scene partitioning strategy that better preserves continuous scene structures during partitioning and reduces cross-region geometric inconsistencies and stitching artifacts through boundary refinement. Second, we develop neighborhood-aware Gaussian organization that extends geometric constraints from individual primitives to their neighborhood organization, encouraging Gaussians to better conform to local surface geometry. Third, we introduce adaptive surface regularization that adjusts the regularization strength according to local geometric characteristics, promoting geometric consistency in structured regions while preserving plausible variations in unstructured regions. Extensive experiments on large-scale aerial photogrammetry benchmarks demonstrate that STARS-GS consistently outperforms the evaluated Gaussian-based methods in surface reconstruction. It increases the average F1-score from 0.640 for the second-best method to 0.698, corresponding to a relative improvement of approximately 9.1\%, demonstrating effective improvements in geometric accuracy and surface completeness.
