LoD-Loc v3：基于实例轮廓对齐的密集城市中通用航空视觉定位
LoD-Loc v3: Generalized Aerial Localization in Dense Cities using Instance Silhouette Alignment
AI总结：
LoD-Loc v3通过实例轮廓对齐和合成数据生成提升密集城市中的航空视觉定位性能，克服了现有方法在跨场景和密集建筑场景中的局限。
摘要：
我们提出了LoD-Loc v3，一种用于密集城市环境中通用航空视觉定位的新方法。尽管先前工作LoD-Loc v2通过语义建筑轮廓对齐低细节城市模型实现定位，但存在两个关键限制：跨场景泛化能力差和在密集建筑场景中频繁失败。我们的方法通过两个关键创新解决这些问题。首先，我们开发了一种新的合成数据生成管道，生成InsLoD-Loc——迄今为止最大的实例分割数据集，包含10万张具有精确实例建筑标注的图像。这使训练模型展现出显著的零样本泛化能力。其次，我们通过将定位范式从语义转换为实例轮廓对齐，显著减少了密集场景中的姿态估计模糊性。大量实验表明，LoD-Loc v3优于现有最先进（SOTA）基线，在跨场景和密集城市场景中均取得显著优势。项目可在https://nudt-sawlab.github.io/LoD-Locv3/上获取。
英文摘要：
We present LoD-Loc v3, a novel method for generalized aerial visual localization in dense urban environments. While prior work LoD-Loc v2 achieves localization through semantic building silhouette alignment with low-detail city models, it suffers from two key limitations: poor cross-scene generalization and frequent failure in dense building scenes. Our method addresses these challenges through two key innovations. First, we develop a new synthetic data generation pipeline that produces InsLoD-Loc - the largest instance segmentation dataset for aerial imagery to date, comprising 100k images with precise instance building annotations. This enables trained models to exhibit remarkable zero-shot generalization capability. Second, we reformulate the localization paradigm by shifting from semantic to instance silhouette alignment, which significantly reduces pose estimation ambiguity in dense scenes. Extensive experiments demonstrate that LoD-Loc v3 outperforms existing state-of-the-art (SOTA) baselines, achieving superior performance in both cross-scene and dense urban scenarios with a large margin. The project is available at https://nudt-sawlab.github.io/LoD-Locv3/.
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。
