用特征高斯体解决俯视图定位中的高度模糊问题。
BevSplat: Resolving Height Ambiguity via Feature-Based Gaussian Primitives for Weakly-Supervised Cross-View Localization
- 用带语义和空间特征的3D高斯体表示地面图像像素
- 在KITTI和VIGOR数据集上定位误差显著降低
- 适合处理广角和针孔相机的跨视角定位任务
本文针对弱监督跨视角定位问题，旨在估计地面相机相对于卫星图像的姿态，但标注存在噪声。现有方法通过鸟瞰图（BEV）合成来弥合跨视角域差距，但因地面图像与卫星高程图缺乏深度信息，常面临高度模糊问题。以往方案或假设地面平坦，或依赖复杂模型如跨视角变换器。本文提出BevSplat，利用基于特征的高斯原语解决高度模糊：将地面图像每个像素表示为包含语义与空间特征的3D高斯体，并合成至BEV特征图以进行相对姿态估计。针对全景查询图像的挑战，引入基于二十面体球的监督策略优化高斯原语。在广泛使用的KITTI与VIGOR数据集上验证，涵盖针孔与全景查询图像，实验结果表明，BevSplat显著优于先前方法。
原文摘要 · Abstract (English)
This paper addresses the problem of weakly supervised cross-view localization, where the goal is to estimate the pose of a ground camera relative to a satellite image with noisy ground truth annotations. A common approach to bridge the cross-view domain gap for pose estimation is Bird's-Eye View (BEV) synthesis. However, existing methods struggle with height ambiguity due to the lack of depth information in ground images and satellite height maps. Previous solutions either assume a flat ground plane or rely on complex models, such as cross-view transformers. We propose BevSplat, a novel method that resolves height ambiguity by using feature-based Gaussian primitives. Each pixel in the ground image is represented by a 3D Gaussian with semantic and spatial features, which are synthesized into a BEV feature map for relative pose estimation. Additionally, to address challenges with panoramic query images, we introduce an icosphere-based supervision strategy for the Gaussian primitives. We validate our method on the widely used KITTI and VIGOR datasets, which include both pinhole and panoramic query images. Experimental results show that BevSplat significantly improves localization accuracy over prior approaches.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。