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

arXiv: https://arxiv.org/abs/2502.09080 · HTML: https://mlsanity.com/paper/2502.09080/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 72 references that are in the map.
- First posted on arXiv 13 Feb 2025.

## Builds on (most cited first, 30 of 54)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction](https://mlsanity.com/paper/2312.12337/) (2023)
- [ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth](https://mlsanity.com/paper/2302.12288/) (2023)
- [Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields](https://mlsanity.com/paper/2312.03203/) (2023)
- [VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval](https://mlsanity.com/paper/2011.12172/) (2020)
- [Lending Orientation to Neural Networks for Cross-view Geo-localization](https://mlsanity.com/paper/1903.12351/) (2019)
- [TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization](https://mlsanity.com/paper/2204.00097/) (2022)
- [Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?](https://mlsanity.com/paper/2206.07959/) (2022)
- [latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction](https://mlsanity.com/paper/2403.16292/) (2024)
- [Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image](https://mlsanity.com/paper/2406.04343/) (2024)
- [Optimal Feature Transport for Cross-View Image Geo-Localization](https://mlsanity.com/paper/1907.05021/) (2019)
- [Beyond Cross-view Image Retrieval: Highly Accurate Vehicle Localization Using Satellite Image](https://mlsanity.com/paper/2204.04752/) (2022)
- [OrienterNet: Visual Localization in 2D Public Maps with Neural Matching](https://mlsanity.com/paper/2304.02009/) (2023)
- [RCBEVDet: Radar-camera Fusion in Bird's Eye View for 3D Object Detection](https://mlsanity.com/paper/2403.16440/) (2024)
- [A Sim2Real Deep Learning Approach for the Transformation of Images from Multiple Vehicle-Mounted Cameras to a Semantically Segmented Image in Bird's Eye View](https://mlsanity.com/paper/2005.04078/) (2020)
- [Improving 2D Feature Representations by 3D-Aware Fine-Tuning](https://mlsanity.com/paper/2407.20229/) (2024)
- [Cross-View Image Synthesis using Conditional GANs](https://mlsanity.com/paper/1803.03396/) (2018)
- [Robust Monocular Depth Estimation under Challenging Conditions](https://mlsanity.com/paper/2308.09711/) (2023)

## Built on by (most cited first, 8 of 8)

- [Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective](https://mlsanity.com/paper/2604.14025/) (2026)
- [RHO: Robust Holistic OSM-Based Metric Cross-View Geo-Localization](https://mlsanity.com/paper/2603.27758/) (2026)
- [Seeing Across Skies and Streets: Feedforward 3D Reconstruction from Satellite, Drone, and Ground Images](https://mlsanity.com/paper/2605.07978/) (2026)
- [Empowering Feed-Forward Reconstruction Models with Metric Scale via Satellite Images](https://mlsanity.com/paper/2606.08205/) (2026)
- [Warp-free Cross-view Geo-localization via Feature-space Consensus Mining](https://mlsanity.com/paper/2608.09321/) (2026)
- [Cross-View Sequential Visual Localization with Spatio-Temporal Context Modeling for Autonomous Driving](https://mlsanity.com/paper/2608.10660/) (2026)
- [OpenCVL: An Open, Diverse, and Large-Scale Dataset for Fine-Grained Cross-View Localization](https://mlsanity.com/paper/2608.25274/) (2026)
- [ARC-Loc: Leveraging Azimuthal Ray Convergence as a Geometric Cue for Direct Cross-View Localization](https://mlsanity.com/paper/2609.04965/) (2026)

## Abstract (arXiv)

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.