{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/computational-miniature-mesoscope-v2-a-deep","title":"Deep-learning-augmented Computational Miniature Mesoscope","arxiv_id":"2205.00123","date":"2022-04-30","proceeding":null,"authors":["Yujia Xue","Qianwan Yang","Guorong Hu","Kehan Guo","Lei Tian"],"abstract":"Fluorescence microscopy is essential to study biological structures and dynamics. However, existing systems suffer from a tradeoff between field-of-view (FOV), resolution, and complexity, and thus cannot fulfill the emerging need of miniaturized platforms providing micron-scale resolution across centimeter-scale FOVs. To overcome this challenge, we developed Computational Miniature Mesoscope (CM$^2$) that exploits a computational imaging strategy to enable single-shot 3D high-resolution imaging across a wide FOV in a miniaturized platform. Here, we present CM$^2$ V2 that significantly advances both the hardware and computation. We complement the 3$\\times$3 microlens array with a new hybrid emission filter that improves the imaging contrast by 5$\\times$, and design a 3D-printed freeform collimator for the LED illuminator that improves the excitation efficiency by 3$\\times$. To enable high-resolution reconstruction across the large imaging volume, we develop an accurate and efficient 3D linear shift-variant (LSV) model that characterizes the spatially varying aberrations. We then train a multi-module deep learning model, CM$^2$Net, using only the 3D-LSV simulator. We show that CM$^2$Net generalizes well to experiments and achieves accurate 3D reconstruction across a $\\sim$7-mm FOV and 800-$\\mu$m depth, and provides $\\sim$6-$\\mu$m lateral and $\\sim$25-$\\mu$m axial resolution. This provides $\\sim$8$\\times$ better axial localization and $\\sim$1400$\\times$ faster speed as compared to the previous model-based algorithm. We anticipate this simple and low-cost computational miniature imaging system will be impactful to many large-scale 3D fluorescence imaging applications.","url_abs":"https://arxiv.org/abs/2205.00123v5","url_pdf":"https://arxiv.org/pdf/2205.00123v5.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"computational-miniature-mesoscope-v2-a-deep","repo_url":"https://github.com/bu-cisl/Computational-Miniature-Mesoscope-CM2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.00123","atlas_url":"https://app.syntology.ai/?focus=2205.00123","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}