LoD-Loc v3：利用实例轮廓对齐实现密集城市中的泛化空中定位
LoD-Loc v3: Generalized Aerial Localization in Dense Cities using Instance Silhouette Alignment
将语义建筑轮廓对齐升级为实例轮廓对齐，并配套生成大规模实例分割合成数据集，为密集城市场景下的跨场景视觉定位提供了可复用的数据与对齐范式。
原文依据 shifting from semantic to instance silhouette alignment, which significantly reduces pose estimation ambiguity in dense scenes
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 LoD-Loc v3，一种用于密集城市环境中泛化空中视觉定位的新方法。先前工作 LoD-Loc v2 通过语义建筑轮廓与低细节城市模型的对齐实现定位，但存在两个关键局限：跨场景泛化能力差，且在密集建筑场景中频繁失败。本方法通过两项关键创新解决这些挑战。首先，我们开发了一个新的合成数据生成流程，生成了 InsLoD-Loc——迄今为止最大的空中影像实例分割数据集，包含 10 万张具有精确实例建筑标注的图像。这使得训练后的模型展现出显著的零样本泛化能力。其次，我们重新构建了定位范式，从语义轮廓对齐转向实例轮廓对齐，显著降低了密集场景中的姿态估计歧义。大量实验表明，LoD-Loc v3 优于现有最优基线，在跨场景和密集城市场景中均以较大幅度取得更优性能。项目见 https://nudt-sawlab.github.io/LoD-Locv3/。
英文原文摘要 1182 字符
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/.