EMGauss：体电子显微镜中基于动态高斯建模的连续切片到三维重建
EMGauss: Continuous Slice-to-3D Reconstruction via Dynamic Gaussian Modeling in Volume Electron Microscopy
把轴向切片序列当作时间维、用 2D 高斯点云随时间的演化来建模各向异性体数据，这一「切片即时序」的建模方式可直接迁移到共聚焦/光片显微、CT 等层析成像的各向异性插值与连续切片合成；教师-学生自举用未观测切片上的高置信预测作伪监督，也是数据稀疏场景下可复用的训练策略。
原文依据 the progression of axial slices is modeled as the temporal evolution of 2D Gaussian point clouds
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论体电子显微镜（vEM）能够对生物结构进行纳米级三维成像，但受采集折衷的限制，所得体数据往往各向异性、轴向分辨率有限。现有深度学习方法试图借助横向先验恢复各向同性，然而其假设在形态各向异性的结构上不再成立。我们提出 EMGauss，一个从平面扫描的二维切片进行三维重建的通用框架，可应用于 vEM，并规避了基于各向同性假设的方法的固有局限。我们的核心创新在于将切片到三维重建重新表述为基于高斯泼溅的三维动态场景渲染问题，其中轴向切片的推进被建模为二维高斯点云的时序演化。为提升数据稀疏情形下的保真度，我们引入教师-学生自举机制，将未观测切片上的高置信预测用作伪监督信号。与基于扩散和 GAN 的重建方法相比，EMGauss 显著提升了插值质量，支持连续切片合成，且无需大规模预训练。除 vEM 之外，它还有望为多种成像领域提供一种可推广的切片到三维解决方案。
英文原文摘要 1296 字符
Volume electron microscopy (vEM) enables nanoscale 3D imaging of biological structures but remains constrained by acquisition trade-offs, leading to anisotropic volumes with limited axial resolution. Existing deep learning methods seek to restore isotropy by leveraging lateral priors; yet their assumptions break down for morphologically anisotropic structures. We present **EMGauss**, a general framework for 3D reconstruction from planar scanned 2D slices with applications in vEM, which circumvents the inherent limitations of isotropy-based approaches. Our key innovation is to reframe slice-to-3D reconstruction as a 3D dynamic scene rendering problem based on Gaussian splatting, where the progression of axial slices is modeled as the temporal evolution of 2D Gaussian point clouds. To enhance fidelity in data-sparse regimes, we incorporate a **Teacher-Student bootstrapping mechanism** that uses high-confidence predictions on unobserved slices as pseudo-supervisory signals. Compared with diffusion- and GAN-based reconstruction methods, EMGauss substantially improves interpolation quality, enables continuous slice synthesis, and eliminates the need for large-scale pretraining. Beyond vEM, it potentially provides a generalizable slice-to-3D solution across diverse imaging domains.