NanoMorph-3D：用于纳米材料重构的端到端物理驱动展开框架
NanoMorph-3D: An End-to-End Physics-Driven Unrolling Framework for Nanomaterial Reconstruction
浏览论文内容
中文总结 AI 辅助
NanoMorph-3D是基于物理驱动展开网络的端到端框架，通过双域策略等技术缓解电子断层扫描的缺失楔问题，实现纳米材料的高精度快速三维重构。
中文摘要 AI 辅助
纳米材料的精确三维表征是揭示结构-性能关系的关键，但标准电子断层扫描受限于固有缺失楔问题，导致传统算法出现严重几何失真，且普遍存在的噪声干扰进一步加剧了该挑战。当前基于学习的方法要么依赖无视物理规律的后处理，要么采用受局部感受野限制的端到端架构，无法捕捉复杂三维拓扑结构。我们提出NanoMorph-3D，这是一个基于综合纳米形态分类学的统一端到端框架。借助显式建模非线性电子衰减的大规模合成数据集，我们设计了将近端梯度下降映射为可学习架构的物理驱动展开网络。为捕捉复杂内部拓扑，我们构建了带有物理归一化的分层注意力机制，以实现长程三维依赖与尺度不变性。关键的是，我们的双域策略利用正弦注意力显式建模物理投影轨迹，强制严格的正弦图一致性以缓解缺失楔伪影。最后，一种无监督双流机制弥合了模拟到真实的差距。实验表明，NanoMorph-3D能以更高保真度和速度重构多种拓扑结构。
英文摘要
Precise 3D characterization of nanomaterials is essential for unlocking structure-property relationships. However, standard electron tomography is fundamentally limited by the missing wedge problem. Consequently, conventional algorithms suffer from severe geometric distortions, a challenge further complicated by pervasive noise interference. Current learning-based methods either rely on physics-blind post-processing or employ end-to-end architectures constrained by local receptive fields, failing to capture complex 3D topologies. We propose NanoMorph-3D, a unified end-to-end framework grounded in a comprehensive Nanomorphological Taxonomy. Powered by a large-scale synthetic dataset explicitly modeling non-linear electron attenuation, we design a Physics-Driven Unrolled Network mapping proximal gradient descent into a learnable architecture. To capture complex internal topologies, we formulate a hierarchical attention mechanism with Physics-Normalization for long-range 3D dependencies and scale invariance. Crucially, our Dual-Domain strategy leverages Sinusoidal Attention to explicitly model physical projection trajectories, enforcing strict sinogram consistency to mitigate missing wedge artifacts. Finally, an unsupervised dual-stream mechanism bridges the simulation-to-reality gap. Experiments demonstrate NanoMorph-3D reconstructs diverse topologies with superior fidelity and speed.
