Metraipolis › archive › dc_ff94c2a3af83
Overcoming Attention Drift: Homogeneity-Heterogeneity Guided Feature Aggregation for Low-Light Remote Sensing Image Enhancement — arXiv:2608.05843
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.05843
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T10:36:19.409Z
- SHA-256 of the archived text
4b3938d802ca26e92ce696ed32ea02cbb4f72a28b10eb9487a75b7e48fa10eee- Stable URL of this page
https://metraipolis.com/documento/dc_ff94c2a3af83
How to cite
Overcoming Attention Drift: Homogeneity-Heterogeneity Guided Feature Aggregation for Low-Light Remote Sensing Image Enhancement — arXiv:2608.05843 — arXiv (en), https://arxiv.org/abs/2608.05843 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff94c2a3af83 (Metraipolis archive dc_ff94c2a3af83, sha256 4b3938d802ca26e92ce696ed32ea02cbb4f72a28b10eb9487a75b7e48fa10eee)
BibTeX
@misc{dcff94c2a3af83,
title = {Overcoming Attention Drift: Homogeneity-Heterogeneity Guided Feature Aggregation for Low-Light Remote Sensing Image Enhancement — arXiv:2608.05843},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.05843},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff94c2a3af83; sha256 4b3938d802ca26e92ce696ed32ea02cbb4f72a28b10eb9487a75b7e48fa10eee},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05843. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Restoring high-fidelity remote sensing imagery from extreme low-light degradation is indispensable for reliable Earth observation and downstream machine vision. However, under severe noise and illumination corruption, existing methods suffer from attention drift, erroneously aggregating features across distinct physical boundaries and causing severe structural blurring and color distortion. To address this, we propose HALO, a dual-prior-driven enhancement framework that formulates enhancement as a guided feature aggregation problem driven by foundation model priors. Specifically, an illumination-invariant semantic prior provides regional homogeneity as a positive bias for content-consistent aggregation, while a pseudo-3D topological prior provides boundary heterogeneity as a negative penalty to strictly prevent cross-boundary confusion. To cooperatively incorporate these two priors, we propose a Homogeneity-Heterogeneity Cooperative Attention Module (H2CAM) to resolve feature conflicts during cross-modal prior fusion. Extensive experiments demonstrate that HALO achieves state-of-the-art performance across 8 challenging synthetic and real-world remote sensing benchmarks, significantly improving physical boundary sharpness and color fidelity while maximizing the preservation of discriminative features for downstream Earth observation tasks. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.05843 — 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 2026-10-31T10:23:31.025Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).