{"ID":2830172,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.10419","arxiv_id":"2512.10419","title":"TransLocNet: Cross-Modal Attention for Aerial-Ground Vehicle Localization with Contrastive Learning","abstract":"Aerial-ground localization is difficult due to large viewpoint and modality gaps between ground-level LiDAR and overhead imagery. We propose TransLocNet, a cross-modal attention framework that fuses LiDAR geometry with aerial semantic context. LiDAR scans are projected into a bird's-eye-view representation and aligned with aerial features through bidirectional attention, followed by a likelihood map decoder that outputs spatial probability distributions over position and orientation. A contrastive learning module enforces a shared embedding space to improve cross-modal alignment. Experiments on CARLA and KITTI show that TransLocNet outperforms state-of-the-art baselines, reducing localization error by up to 63% and achieving sub-meter, sub-degree accuracy. These results demonstrate that TransLocNet provides robust and generalizable aerial-ground localization in both synthetic and real-world settings.","short_abstract":"Aerial-ground localization is difficult due to large viewpoint and modality gaps between ground-level LiDAR and overhead imagery. We propose TransLocNet, a cross-modal attention framework that fuses LiDAR geometry with aerial semantic context. LiDAR scans are projected into a bird's-eye-view representation and aligned...","url_abs":"https://arxiv.org/abs/2512.10419","url_pdf":"https://arxiv.org/pdf/2512.10419v1","authors":"[\"Phu Pham\",\"Damon Conover\",\"Aniket Bera\"]","published":"2025-12-11T08:34:26Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}