Depth-Aware Machine Learning for 3D Reconstruction of Fibrous Porous Electrodes by FIB-SEM Tomography.

Quantitative three-dimensional reconstruction of porous polymers with sub-micrometer feature sizes is central to understanding and designing electrochemical interfaces and membranes. However, focused ion beam-scanning electron microscopy tomography combined with conventional segmentation techniques cannot readily reconstruct complex disordered morphologies such as fibers. Standard segmentation workflows misclassify out-of-plane material as in-plane material, distorting the reconstructed pore network, fiber connectivity, and interface area. Here, we introduce an annotation-free, depth-aware machine-learning framework that combines monocular depth estimation, trained on macroscale images, with unsupervised clustering to separate in-plane polymer cross-sections from subsurface contributions in serial FIB-SEM tomography images. Applied to copper-coated electrospun poly(vinylidene fluoride-co-hexafluoropropylene) fiber mats, the approach produces 3D reconstructions that preserve fibrous morphology more faithfully than conventional supervised and unsupervised segmentation. Quantitative validation against capillary flow porometry, pycnometry, and high-resolution wide-angle X-ray computed tomography demonstrates improved agreement across pore cross-section diameter, fiber volume ratio, and Cu depth decrease metrics. This work establishes depth-aware segmentation as a transferable strategy from real-scale to nanoscale imaging, requiring no labeled training data and enabling accurate 3D segmentation and reconstruction from SEM images. This approach opens a path toward more reliable structure-property relationships in disordered porous polymer materials.