BevSplat: Resolving Height Ambiguity via Feature-Based Gaussian Primitives for Weakly-Supervised Cross-View Localization

doi:arXiv:2502.09080

	BevSplat: Resolving Height Ambiguity via Feature-Based Gaussian Primitives for Weakly-Supervised Cross-View Localization
	Wang, Qiwei; Wu, Shaoxun; Shi, Yujiao
	2025-02-13
状态	已发表
摘要	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.
语种	英语
DOI	arXiv:2502.09080
相关网址	查看原文
出处	Arxiv
收录类别	PPRN.PPRN
WOS记录号	PPRN:121556956
WOS类目	Computer Science, Software Engineering
文献类型	预印本
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/514093
专题	信息科学与技术学院_PI研究组_师玉娇组
通讯作者	Shi, Yujiao
作者单位	Shanghaitech Univ, Shanghai, Peoples R China
推荐引用方式 GB/T 7714	Wang, Qiwei,Wu, Shaoxun,Shi, Yujiao. BevSplat: Resolving Height Ambiguity via Feature-Based Gaussian Primitives for Weakly-Supervised Cross-View Localization. 2025.