Salvato in:
Dettagli Bibliografici
Autori principali: Deng, Zhantao, Er-Rafik, Mériem, Sushko, Anna, Hébert, Cécile, Fua, Pascal
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.06516
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913084076982272
author Deng, Zhantao
Er-Rafik, Mériem
Sushko, Anna
Hébert, Cécile
Fua, Pascal
author_facet Deng, Zhantao
Er-Rafik, Mériem
Sushko, Anna
Hébert, Cécile
Fua, Pascal
contents Limited-angle electron tomography aims to reconstruct 3D shapes from 2D projections of Transmission Electron Microscopy (TEM) within a restricted range and number of tilting angles, but it suffers from the missing-wedge problem that causes severe reconstruction artifacts. Deep learning approaches have shown promising results in alleviating these artifacts, yet they typically require large high-quality training datasets with known 3D ground truth which are difficult to obtain in electron microscopy. To address these challenges, we propose TEMDiff, a novel 3D diffusion-based iterative reconstruction framework. Our method is trained on readily available volumetric FIB-SEM data using a simulator that maps them to TEM tilt series, enabling the model to learn realistic structural priors without requiring clean TEM ground truth. By operating directly on 3D volumes, TEMDiff implicitly enforces consistency across slices without the need for additional regularization. On simulated electron tomography datasets with limited angular coverage, TEMDiff outperforms state-of-the-art methods in reconstruction quality. We further demonstrate that a trained TEMDiff model generalizes well to real-world TEM tilts obtained under different conditions and can recover accurate structures from tilt ranges as narrow as 8 degrees, with 2-degree increments, without any retraining or fine-tuning.
format Preprint
id arxiv_https___arxiv_org_abs_2510_06516
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Limited-Angle Tomography Reconstruction via Projector Guided 3D Diffusion
Deng, Zhantao
Er-Rafik, Mériem
Sushko, Anna
Hébert, Cécile
Fua, Pascal
Computer Vision and Pattern Recognition
Limited-angle electron tomography aims to reconstruct 3D shapes from 2D projections of Transmission Electron Microscopy (TEM) within a restricted range and number of tilting angles, but it suffers from the missing-wedge problem that causes severe reconstruction artifacts. Deep learning approaches have shown promising results in alleviating these artifacts, yet they typically require large high-quality training datasets with known 3D ground truth which are difficult to obtain in electron microscopy. To address these challenges, we propose TEMDiff, a novel 3D diffusion-based iterative reconstruction framework. Our method is trained on readily available volumetric FIB-SEM data using a simulator that maps them to TEM tilt series, enabling the model to learn realistic structural priors without requiring clean TEM ground truth. By operating directly on 3D volumes, TEMDiff implicitly enforces consistency across slices without the need for additional regularization. On simulated electron tomography datasets with limited angular coverage, TEMDiff outperforms state-of-the-art methods in reconstruction quality. We further demonstrate that a trained TEMDiff model generalizes well to real-world TEM tilts obtained under different conditions and can recover accurate structures from tilt ranges as narrow as 8 degrees, with 2-degree increments, without any retraining or fine-tuning.
title Limited-Angle Tomography Reconstruction via Projector Guided 3D Diffusion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.06516