Metraipolis › archive › dc_ad680fc82a51

GAAT: Geometry-Aware Alignment Transformer for Multimodal UAV Perception — arXiv:2608.27971

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.27971
License (as archived)
CC0-1.0
Archived
2026-10-17T11:33:04.420Z
SHA-256 of the archived text
0ed3fb080ab7250b2c491016de786fed28d82d8b4d0f7f77c2b269d94fd34ef6
Stable URL of this page
https://metraipolis.com/documento/dc_ad680fc82a51

How to cite

GAAT: Geometry-Aware Alignment Transformer for Multimodal UAV Perception — arXiv:2608.27971 — arXiv (en), https://arxiv.org/abs/2608.27971 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ad680fc82a51 (Metraipolis archive dc_ad680fc82a51, sha256 0ed3fb080ab7250b2c491016de786fed28d82d8b4d0f7f77c2b269d94fd34ef6)
BibTeX
@misc{dcad680fc82a51,
  title = {GAAT: Geometry-Aware Alignment Transformer for Multimodal UAV Perception — arXiv:2608.27971},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.27971},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ad680fc82a51; sha256 0ed3fb080ab7250b2c491016de786fed28d82d8b4d0f7f77c2b269d94fd34ef6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27971. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Unmanned aerial vehicle (UAV) multimodal perception integrates visible (RGB), infrared (IR), synthetic aperture radar (SAR), and depth sensors for scene understanding under diverse conditions. However, differences in optics, resolution, and mounting often limit practical systems to global or image-center alignment. After tokenization, parallax, platform motion, and lens distortion can shift corresponding patch centers across modalities, weakening the spatial correspondence assumed by dense contrastive learning and cross-modal fusion. We propose GAAT (Geometry-Aware Alignment Transformer), an alignment-first pretrained model that estimates local correspondence reliability before cross-modal interaction. GAAT introduces syncPATC, which learns patch-center consistency under synchronized view transformations without correspondence annotations. It emits geometric priors, including token and query confidence, query centers, and sub-token offsets, that identify reliable local anchors across residual misalignment. Guided by these priors, MG-Sparse-MMA performs query-mediated sparse fusion over top-K_s reliable regions, replacing dense all-patch interaction with geometry-calibrated local updates. RA-QCGCL aligns pretraining supervision with this sparse query bottleneck through reliable patch-to-patch, patch-to-query, and query-to-query contrastive branches. We introduce UAVMeta and StateBench, which provide four acquisition-state scores derived from platform telemetry and image statistics: camera reliability, observation scale, viewpoint stability, and flight maneuver complexity. Extensive experiments across six downstream tasks demonstrate consistently superior transfer performance, establishing GAAT as a state-of-the-art multimodal foundation model for UAV perception. StateBench further enables a systematic diagnosis of real-world acquisition conditions.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-31 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.27971 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T11:10:05.284Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).