Fose: Fusion of One-Step Diffusion and End-to-End Network for Pansharpening

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Kai, Lin, Zeli, Wang, Weibo, Kong, Linghe, Zhang, Yulun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911327662899200
author Liu, Kai
Lin, Zeli
Wang, Weibo
Kong, Linghe
Zhang, Yulun
author_facet Liu, Kai
Lin, Zeli
Wang, Weibo
Kong, Linghe
Zhang, Yulun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_17202
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fose: Fusion of One-Step Diffusion and End-to-End Network for Pansharpening
Liu, Kai
Lin, Zeli
Wang, Weibo
Kong, Linghe
Zhang, Yulun
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title Fose: Fusion of One-Step Diffusion and End-to-End Network for Pansharpening
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2512.17202