MicroFM：面向各向同性显微重建的物理引导流匹配
MicroFM: Physics-guided Flow Matching for Isotropic Microscopy Reconstruction
把物理点扩散函数（PSF）匹配的合成数据与流匹配生成模型结合，并用连续隐式几何先验约束体数据，为各向异性退化下的三维重建提供了可复用的「物理退化建模 + 生成式复原」范式。
原文依据 MicroFM also introduces a physics-guided flow-matching framework for isotropic microscopy reconstruction, guided by a continuous implicit geometry prior
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论各向同性显微重建仍具挑战性，因为光学系统中的各向异性点扩散函数导致轴向分辨率显著变差，并妨碍准确的三维分析。硬件策略虽可逼近各向同性，但复杂、昂贵、易受旁瓣影响，且会引入光毒性。深度学习方法降低了采集负担，但合成流程往往依赖与物理退化不匹配的高斯模糊，且许多方法独立处理二维切片而缺乏显式的体几何约束，导致重建保真度低。为应对这些挑战，本文提出 MicroFM，其使用与目标显微镜相匹配的物理点扩散函数合成逼真的训练数据。MicroFM 还引入了一个物理引导的流匹配框架用于各向同性显微重建，该框架由连续的隐式几何先验引导，以实现高保真的各向同性恢复。在四个荧光显微系统与数据集上，MicroFM 取得了最优性能，生成的结构更锐利、频谱更接近各向同性，并在全参考与无参考指标上均取得显著提升。
英文原文摘要 1185 字符
Isotropic microscopy reconstruction remains challenging because the anisotropic point spread function in optical systems yields much poorer axial resolution and hampers accurate 3D analysis. Hardware strategies can approach isotropy, yet they are complex, costly, susceptible to sidelobes, and introduce phototoxicity. Deep learning approaches reduce acquisition burden, yet synthetic pipelines often rely on Gaussian blur mismatched to physical degradation, and many methods lack explicit volumetric geometry constraints as they process 2D slices independently, resulting in low-fidelity reconstructions. To address these challenges, we present MicroFM, which synthesizes realistic training data using physical PSFs matched to the target microscope. MicroFM also introduces a physics-guided flow-matching framework for isotropic microscopy reconstruction, guided by a continuous implicit geometry prior to achieve high-fidelity isotropic recovery. Across four fluorescence microscopy systems and datasets, MicroFM achieves state-of-the-art (SOTA) performance, producing sharper structures, more isotropic spectra, and substantial gains in both full-reference and no-reference metrics.