基于非平衡最优传输的流匹配优化用于快速全色锐化
Taming Flow Matching with Unbalanced Optimal Transport into Fast Pansharpening
AI总结：
针对现有扩散模型全色锐化多步采样计算开销大、减步会降质的问题，提出整合非平衡最优传输对偶形式的OTFM框架，实现单步高质量全色锐化，性能媲美或超越现有方法。
摘要：
全色锐化是遥感领域中融合高分辨率全色图像与多光谱图像的关键任务，已引发大量研究关注。近期基于随机微分方程（SDE）的扩散模型相关进展展现出了当前最优的性能。但SDE固有的多步采样过程会带来巨大的计算开销，阻碍了实际部署。现有方法虽采用高效采样器、知识蒸馏或重训练来减少采样步数（例如从1000步降至更少步数），但这类方法往往会牺牲融合质量。本研究中，我们提出最优传输流匹配（OTFM）框架，该框架整合非平衡最优传输（UOT）的对偶形式，可实现单步、高质量的全色锐化。与传统最优传输公式强制严格的分布对齐不同，UOT放宽了边缘约束以提升建模灵活性，可适配遥感数据中固有的光谱与空间差异。此外，我们在UOT目标中加入了任务特定的正则化项，提升了流模型的鲁棒性。OTFM框架支持无仿真训练与单步推理，同时严格遵循全色锐化的约束条件。在多个数据集上的实验评估表明，OTFM仅需一步采样，性能就可媲美甚至超越以往基于回归的模型以及主流的基于扩散的方法。代码可在https://github.com/294coder/PAN-OTFM获取。
英文摘要：
Pansharpening, a pivotal task in remote sensing for fusing high-resolution panchromatic and multispectral imagery, has garnered significant research interest. Recent advancements employing diffusion models based on stochastic differential equations (SDEs) have demonstrated state-of-the-art performance. However, the inherent multi-step sampling process of SDEs imposes substantial computational overhead, hindering practical deployment. While existing methods adopt efficient samplers, knowledge distillation, or retraining to reduce sampling steps (e.g., from 1,000 to fewer steps), such approaches often compromise fusion quality. In this work, we propose the Optimal Transport Flow Matching (OTFM) framework, which integrates the dual formulation of unbalanced optimal transport (UOT) to achieve one-step, high-quality pansharpening. Unlike conventional OT formulations that enforce rigid distribution alignment, UOT relaxes marginal constraints to enhance modeling flexibility, accommodating the intrinsic spectral and spatial disparities in remote sensing data. Furthermore, we incorporate task-specific regularization into the UOT objective, enhancing the robustness of the flow model. The OTFM framework enables simulation-free training and single-step inference while maintaining strict adherence to pansharpening constraints. Experimental evaluations across multiple datasets demonstrate that OTFM matches or exceeds the performance of previous regression-based models and leading diffusion-based methods while only needing one sampling step. Codes are available at https://github.com/294coder/PAN-OTFM.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
