Lifting Vision: Ground to Aerial Localization with Reasoning Guided Planning
Soham Pahari, M. Srinivas
TL;DR
ViReLoc introduces a unified visual reasoning framework for ground-to-aerial localization and planning that eschews language-dependent reasoning in favor of sequential visual states and map-grounded navigation. The method comprises three phases: a canvas construction stage that builds a geospatial scaffold, a cross-view localization module that anchors ground observations to satellite priors, and a reinforcement-learning-based visual planning module that generates geo-consistent trajectories. Key contributions include a DINOv3-based satellite encoder with bidirectional contrastive alignment, a differentiable planner leveraging A* and autoregressive foresight, and a geo-consistent reward design that ties progression to spatial alignment. Experiments across CVGL benchmarks and CARLA-based planning tasks demonstrate state-of-the-art localization accuracy, robust cross-view generalization, and effective end-to-end navigation without real-time GPS data, highlighting the practical impact for secure, interpretable navigation systems.
Abstract
Multimodal intelligence development recently show strong progress in visual understanding and high level reasoning. Though, most reasoning system still reply on textual information as the main medium for inference. This limit their effectiveness in spatial tasks such as visual navigation and geo-localization. This work discuss about the potential scope of this field and eventually propose an idea visual reasoning paradigm Geo-Consistent Visual Planning, our introduced framework called Visual Reasoning for Localization, or ViReLoc, which performs planning and localization using only visual representations. The proposed framework learns spatial dependencies and geometric relations that text based reasoning often suffer to understand. By encoding step by step inference in the visual domain and optimizing with reinforcement based objectives, ViReLoc plans routes between two given ground images. The system also integrates contrastive learning and adaptive feature interaction to align cross view perspectives and reduce viewpoint differences. Experiments across diverse navigation and localization scenarios show consistent improvements in spatial reasoning accuracy and cross view retrieval performance. These results establish visual reasoning as a strong complementary approach for navigation and localization, and show that such tasks can be performed without real time global positioning system data, leading to more secure navigation solutions.