{"ID":2892654,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.15059","arxiv_id":"2507.15059","title":"Rethinking Pan-sharpening: A New Training Process for Full-Resolution Generalization","abstract":"The field of pan-sharpening has recently seen a trend towards increasingly large and complex models, often trained on single, specific satellite datasets. This one-dataset, one-model approach leads to high computational overhead and impractical deployment. More critically, it overlooks a core challenge: poor generalization from reduced-resolution (RR) training to real-world full-resolution (FR) data. In response to this issue, we challenge this paradigm. We introduce a multiple-in-one training strategy, where a single, compact model is trained simultaneously on three distinct satellite datasets (WV2, WV3, and GF2). Our experiments show the primary benefit of this unified strategy is a significant and universal boost in FR generalization (QNR) across all tested models, directly addressing this overlooked problem. This paradigm also inherently solves the one-model-per-dataset challenge, and we support it with a highly reproducible, dependency-free codebase for true usability. Finally, we propose PanTiny, a lightweight framework designed specifically for this new, robust paradigm. We demonstrate it achieves a superior performance-to-efficiency balance, proving that principled, simple and robust design is more effective than brute-force scaling in this practical setting. Our work advocates for a community-wide shift towards creating efficient, deployable, and truly generalizable models for pan-sharpening. The code is open-sourced at https://github.com/Zirconium233/PanTiny.","short_abstract":"The field of pan-sharpening has recently seen a trend towards increasingly large and complex models, often trained on single, specific satellite datasets. This one-dataset, one-model approach leads to high computational overhead and impractical deployment. More critically, it overlooks a core challenge: poor generaliza...","url_abs":"https://arxiv.org/abs/2507.15059","url_pdf":"https://arxiv.org/pdf/2507.15059v3","authors":"[\"Ran Zhang\",\"Xuanhua He\",\"Li Xueheng\",\"Ke Cao\",\"Liu Liu\",\"Wenbo Xu\",\"Fang Jiabin\",\"Yang Qize\",\"Jie Zhang\"]","published":"2025-07-20T17:50:49Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":612007,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2892654,"paper_url":"https://arxiv.org/abs/2507.15059","paper_title":"Rethinking Pan-sharpening: A New Training Process for Full-Resolution Generalization","repo_url":"https://github.com/Zirconium233/PanTiny","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}