Metraipolis › archive › dc_d3ffe50e1434
RegisterBridgeMM: A Register-Centric Framework for RGB-Infrared Object Detection — arXiv:2608.04833
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.04833
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T11:48:12.096Z
- SHA-256 of the archived text
fa91edc4fb144cd92dc5477b670d5ee4f278f0a302300e70678b2326904ea381- Stable URL of this page
https://metraipolis.com/documento/dc_d3ffe50e1434
How to cite
RegisterBridgeMM: A Register-Centric Framework for RGB-Infrared Object Detection — arXiv:2608.04833 — arXiv (en), https://arxiv.org/abs/2608.04833 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d3ffe50e1434 (Metraipolis archive dc_d3ffe50e1434, sha256 fa91edc4fb144cd92dc5477b670d5ee4f278f0a302300e70678b2326904ea381)
BibTeX
@misc{dcd3ffe50e1434,
title = {RegisterBridgeMM: A Register-Centric Framework for RGB-Infrared Object Detection — arXiv:2608.04833},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.04833},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d3ffe50e1434; sha256 fa91edc4fb144cd92dc5477b670d5ee4f278f0a302300e70678b2326904ea381},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04833. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
RGB-infrared (RGB-IR) object detection benefits from complementary visible and thermal cues, but effective fusion remains challenging under illumination changes, weather variation, and cluttered scenes. Existing RGB-IR fusion methods often trade expressive patch-level interaction for lighter but more constrained adaptation mechanisms. We empirically observe that pretrained register tokens contain both modality-shared and modality-specific information on paired RGB-IR inputs, suggesting that they can serve as a compact substrate for cross-modal communication. Building on this observation, we propose RegisterBridgeMM, a register-mediated fusion framework organized as a three-stage register lifecycle. Aggregate preserves per-modality register summarization inherited from pretraining; Bridge performs bidirectional register-to-patch reading with consensus-residual regulation; and Project translates the resulting register summary into spatially adaptive calibration of patch features. This register pathway avoids dense patch-to-patch cross-modal interaction while preserving the pretrained patch representation. With both backbone streams frozen, RegisterBridgeMM achieves the highest mAP50-95 among the evaluated methods on all four benchmarks: LLVIP, M3FD, DroneVehicle, and FLIR-Aligned. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-06 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.04833 — 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 2026-10-31T11:37:40.723Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).