{"id":"doi:10.1038/s41598-024-56910-9","kind":"article","title":"Generating 3D images of material microstructures from a single 2D image: a denoising diffusion approach","authors":["Johan Phan","Muhammad Sarmad","Leonardo Carlos Ruspini","Gabriel Hanssen Kiss","Frank Lindseth"],"author_count":5,"year":2024,"published":"2024-03-18","venue":"Scientific Reports","cited_by":40,"doi":"10.1038/s41598-024-56910-9","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1038/s41598-024-56910-9","archive_url":"https://space-kitty.com/papers/doi:10.1038/s41598-024-56910-9","updated":null,"pmid":"38499588","pmcid":null,"openalex_id":"W4392913623","pdf_url":"https://www.nature.com/articles/s41598-024-56910-9.pdf","abstract":"Three-dimensional (3D) images provide a comprehensive view of material microstructures, enabling numerical simulations unachievable with two-dimensional (2D) imaging alone. However, obtaining these 3D images can be costly and constrained by resolution limitations. We introduce a novel method capable of generating large-scale 3D images of material microstructures, such as metal or rock, from a single 2D image. Our approach circumvents the need for 3D image data while offering a cost-effective, high-resolution alternative to existing imaging techniques. Our method combines a denoising diffusion probabilistic model with a generative adversarial network framework. To compensate for the lack of 3D training data, we implement chain sampling, a technique that utilizes the 3D intermediate outputs obtained by reversing the diffusion process. During the training phase, these intermediate outputs are guided by a 2D discriminator. This technique facilitates our method's ability to gradually generate 3D images that accurately capture the geometric properties and statistical characteristics of the original 2D input. This study features a comparative analysis of the 3D images generated by our method, SliceGAN (the current state-of-the-art method), and actual 3D micro-CT images, spanning a diverse set of rock and metal types. The results shown an improvement of up to three times in the Frechet inception distance score, a typical metric for evaluating the performance of image generative models, and enhanced accuracy in derived properties compared to SliceGAN. The potential of our method to produce high-resolution and statistically representative 3D images paves the way for new applications in material characterization and analysis domains.","abstract_license":"CC-BY (publisher license, via OpenAlex)","license":"cc-by","is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["Generative Adversarial Networks and Image Synthesis"],"details":null,"provenance":"openalex","attribution":"Abstract of \"Generating 3D images of material microstructures from a single 2D image: a denoising diffusion approach\" by Johan Phan, Muhammad Sarmad, Leonardo Carlos Ruspini et al., https://doi.org/10.1038/s41598-024-56910-9, used under its Creative Commons Attribution license (CC-BY); markup removed, otherwise unmodified.","topics":[{"slug":"generative-multimodal","name":"Generative & Multimodal Models","domain_slug":"ai"}],"cited_in_dossiers":[]}