BevSplat: Resolving Height Ambiguity via Feature-Based Gaussian Primitives for Weakly-Supervised Cross-View Localization
It addresses pose estimation between ground and satellite images for applications like autonomous navigation, but is incremental as it builds on existing BEV synthesis methods.
This paper tackles the problem of weakly supervised cross-view localization by resolving height ambiguity in Bird's-Eye View synthesis, resulting in significant improvements in localization accuracy on KITTI and VIGOR datasets.
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.