Search papers, labs, and topics across Lattice.
This paper introduces NanoMorph-3D, an end-to-end framework that addresses the limitations of traditional electron tomography in 3D nanomaterial reconstruction by integrating a Physics-Driven Unrolled Network with a hierarchical attention mechanism. The framework effectively mitigates the missing wedge problem and noise interference by employing a Dual-Domain strategy that models physical projection trajectories, resulting in improved fidelity and speed in reconstructing complex nanostructures. Experimental results show that NanoMorph-3D significantly outperforms existing methods, enabling precise characterization crucial for understanding structure-property relationships in nanomaterials.
NanoMorph-3D achieves unprecedented reconstruction fidelity and speed by seamlessly integrating physics-driven modeling with advanced attention mechanisms, transforming how we analyze nanomaterials.
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.
