{"ID":2826894,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.17202","arxiv_id":"2512.17202","title":"Fose: Fusion of One-Step Diffusion and End-to-End Network for Pansharpening","abstract":"Pansharpening is a significant image fusion task that fuses low-resolution multispectral images (LRMSI) and high-resolution panchromatic images (PAN) to obtain high-resolution multispectral images (HRMSI). The development of the diffusion models (DM) and the end-to-end models (E2E model) has greatly improved the frontier of pansharping. DM takes the multi-step diffusion to obtain an accurate estimation of the residual between LRMSI and HRMSI. However, the multi-step process takes large computational power and is time-consuming. As for E2E models, their performance is still limited by the lack of prior and simple structure. In this paper, we propose a novel four-stage training strategy to obtain a lightweight network Fose, which fuses one-step DM and an E2E model. We perform one-step distillation on an enhanced SOTA DM for pansharping to compress the inference process from 50 steps to only 1 step. Then we fuse the E2E model with one-step DM with lightweight ensemble blocks. Comprehensive experiments are conducted to demonstrate the significant improvement of the proposed Fose on three commonly used benchmarks. Moreover, we achieve a 7.42 speedup ratio compared to the baseline DM while achieving much better performance. The code and model are released at https://github.com/Kai-Liu001/Fose.","short_abstract":"Pansharpening is a significant image fusion task that fuses low-resolution multispectral images (LRMSI) and high-resolution panchromatic images (PAN) to obtain high-resolution multispectral images (HRMSI). The development of the diffusion models (DM) and the end-to-end models (E2E model) has greatly improved the fronti...","url_abs":"https://arxiv.org/abs/2512.17202","url_pdf":"https://arxiv.org/pdf/2512.17202v1","authors":"[\"Kai Liu\",\"Zeli Lin\",\"Weibo Wang\",\"Linghe Kong\",\"Yulun Zhang\"]","published":"2025-12-19T03:28:39Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":605769,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2826894,"paper_url":"https://arxiv.org/abs/2512.17202","paper_title":"Fose: Fusion of One-Step Diffusion and End-to-End Network for Pansharpening","repo_url":"https://github.com/Kai-Liu001/Fose","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}