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

NeurIPSSpotlight2025

Authors
Qiwei Wang, Wu Shaoxun, Yujiao Shi
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

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 annotatio…

Opening excerpt from the authors’ abstract. source

Read the paper

← All NeurIPS 2025 Spotlight papers · Browse the whole archive