用流匹配引导的深度展开网络，提升高光谱图像重建质量。
Flow-Matching Guided Deep Unfolding for Hyperspectral Image Reconstruction
- 将流匹配生成先验嵌入深度展开框架，结合优化可解释性与生成能力。
- 引入均速度损失增强流的一致性，显著改善重建精度与鲁棒性。
- 适合需要高质量重建的遥感、医学成像等场景，尤其在压缩测量下表现优异。
高光谱成像（HSI）提供丰富的时空谱信息，但受限于硬件和三维数据重构难度，获取成本高昂。尽管压缩感知系统如CASSI提升了效率，准确重建仍面临严重退化与精细光谱细节丢失的挑战。本文提出首个将流匹配融入HSI重建的深度展开网络——FMU，通过在深度展开框架中嵌入流匹配的生成先验，实现更优重建。为强化学习动态，设计均速度损失以保证流的全局一致性，提升重建鲁棒性与准确性。该混合结构融合了基于优化方法的可解释性与流匹配的生成能力。在模拟与真实数据集上的大量实验表明，FMU显著优于现有方法。代码与模型将公开于https://github.com/YiAi03/FMU。
原文摘要 · Abstract (English)
Hyperspectral imaging (HSI) provides rich spatial-spectral information but remains costly to acquire due to hardware limitations and the difficulty of reconstructing three-dimensional data from compressed measurements. Although compressive sensing systems such as CASSI improve efficiency, accurate reconstruction is still challenged by severe degradation and loss of fine spectral details. We propose the Flow-Matching-guided Unfolding network (FMU), which, to our knowledge, is the first to integrate flow matching into HSI reconstruction by embedding its generative prior within a deep unfolding framework. To further strengthen the learned dynamics, we introduce a mean velocity loss that enforces global consistency of the flow, leading to a more robust and accurate reconstruction. This hybrid design leverages the interpretability of optimization-based methods and the generative capacity of flow matching. Extensive experiments on both simulated and real datasets show that FMU significantly outperforms existing approaches in reconstruction quality. Code and models will be available at https://github.com/YiAi03/FMU.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。