Skip to content

Imaging and Computational Imaging

Optical imaging, microscopy and computational imaging, including AI-assisted image reconstruction and inverse problem solving.

Latest updates

Items 1–16 of 16
Oct 14Wed
  1. optics.org (SPIE Industry News)Optics industryOptics and AI57

    US Army Research Office Awards $19.2 Million Grant to UCF-Led Team

    A team led by the University of Central Florida (UCF) will receive a five-year, $19.2 million grant from the US Army Research Office to study light propagation and control in complex dynamic environments. The project, led by Guifang Li, will explore weak backscattering coherent measurement, inverse methods, AI analysis and multi-plane light conversion, with the goal of measuring and rapidly correcting optical field distortions when remote sensors or beacons cannot be placed. Potential applications include directed-energy systems, biological tissue imaging, laser medicine, remote sensing and free-space optical communications.

Oct 13Tue
Oct 9Fri
  1. Phys.org Optics & PhotonicsOptics industryOptics and AI61

    SF-PULSE Lensless Imaging Enables Stain-Free Long-Term Monitoring of Living Cells

    Researchers proposed the SF-PULSE lensless imaging method, which can monitor living cells over long periods without staining, and successfully imaged and reconstructed glioblastoma cells.

    Why we recommend it: The source demonstrates an imaging route that replaces lenses with computational reconstruction, offering insights for low-cost microscopy

Oct 8Thu
  1. Photonics.comOptics industryOptics and AI61

    Frequency Combs and Deep Learning Enable Fast, High-Fidelity Ghost Imaging

    Ghost imaging replaces pixelated sensors with correlation measurements between structured illumination and a single-pixel detector. Researchers combined an optical frequency comb with deep learning to achieve faster, higher-fidelity ghost imaging.

    Why we recommend it: The original article shows the combination of frequency comb illumination with AI reconstruction, a typical example of optics and AI working together in computational imaging

Oct 7Wed
Oct 5Mon
  1. Optics & Photonics NewsOptics industryOptics and AI63

    UCLA Digital-Optical Hybrid Processor Identifies Multiple Deepfake Videos Simultaneously

    A team from the Ozcan lab at the University of California, Los Angeles has developed a digital-optical hybrid system that can identify deepfake videos simultaneously across multiple channels.

    Why we recommend it: The source article presents a new application of a diffractive optical processor for AI vision tasks, illustrating a practical use case for optical computing

Sep 30Wed
Sep 22Tue
Sep 16Wed
Sep 10Thu
  1. Xi'an Institute of Optics and Fine Mechanics (XIOPM) · Research ProgressOptics industryOptics and AI59

    Xi'an Institute of Optics and Mechanics Proposes New Framework for AUV Underwater Optical Docking

    A team led by Wu Guojun at the Xi'an Institute of Optics and Mechanics has proposed PGF-ULB, an underwater light beacon detection and localization framework combining physics guidance and geometric constraints, for AUV optical docking in complex underwater environments.

    Why we recommend it: The original text provides specific data and details that help assess the actual progress in this direction

Aug 26Wed
  1. Anhui Institute of Optics and Fine Mechanics (AIOFM) · Research ProgressOptics industryOptics and AI42

    AIOFM Proposes GeoAdapt and Freq-LoRA to Enhance Intelligent Sensing of Aerial Targets in Ground-Based Optical Remote Sensing

    A team from the Optoelectronics Center at the Anhui Institute of Optics and Fine Mechanics (AIOFM) published two papers in Remote Sensing, proposing the lightweight keypoint localization framework GeoAdapt and the frequency-domain low-rank adaptation segmentation method Freq-LoRA for aerial target sensing in ground-based optical remote sensing. GeoAdapt has only 5.95M parameters and achieves PCK@0.05D of 89.3%; Freq-LoRA requires just 559K trainable parameters and reaches a mean intersection-over-union of 0.904 across five simulated weather datasets, or 96.1% of full fine-tuning performance.

Jun 12Fri
  1. Anhui Institute of Optics and Fine Mechanics (AIOFM) · Research ProgressOptics industryOptics and AI39

    AIOFM Builds Digital Hydrogel Fluorescence-Enhanced Microsphere System for Amplification-Free Relative Quantification of CRISPR Nucleic Acids

    The Optoelectronics Center at the Anhui Institute of Optics and Fine Mechanics published a paper in Analytical Chemistry describing CrisprDEM, a digital hydrogel fluorescence-enhanced microsphere detection system based on CRISPR/Cas12a that enables amplification-free relative quantification of nucleic acids. The system uses hydrogel microspheres to enrich fluorescent reporter molecules, achieving a thousandfold-level enhancement of the fluorescence signal. A microfluidic chip then spreads the microspheres into a monolayer for imaging, and a K-means algorithm distinguishes positive from negative microspheres, with the proportion of positive microspheres used for quantification.

May 19Tue
  1. Xi'an Institute of Optics and Fine Mechanics (XIOPM) · Research ProgressOptics industryOptics and AI61

    Theoretical Breakthrough in Fourier Ptychographic Microscopy

    The State Key Laboratory of Ultrafast Optics and Technology has established a prior-free digital reconstruction theory in the field of FPM.

    Why we recommend it: The original article provides specific data and details that help assess the actual progress in this direction

Sep 23Tue
  1. Hangzhou Institute of Optics and Fine Mechanics · Industry NewsOptics industryOptics and AI36

    Rueminkang Launches DF600, China's First Fully Domestic Laser Fundus Camera

    Rueminkang (Zhejiang) Medical Technology Co., Ltd. has launched the DF600 series, China's first fully domestic laser fundus camera. Using laser as its sole light source combined with confocal pinhole technology, the device delivers layered imaging of the fundus. It covers a minimum field of 130 degrees, with intelligent stitching extending coverage to up to 260 degrees, requires only a 2 mm pupil without dilation, and captures images in 0.1 seconds. Built-in proprietary AI algorithms, requiring no internet connection, identify the optic disc, blood vessels, macula and hemorrhages. The DF600 has been deployed in endocrinology, health screening, emergency care and other settings.

Jan 28Tue
  1. Google Blog · XR/AROptics and AI40

    Google Recounts the Development of the Pixel Camera's Add Me Group Photo Feature

    Google describes how the Pixel camera's Add Me feature was developed. The feature merges two photos taken sequentially of the same scene, allowing the photographer to appear in the group shot. The second photographer sees an augmented reality overlay of the first photo to align the composition. The feature relies on multiple machine learning models running locally on the TPU of the Tensor G4 chip. Add Me launched with the Pixel 9 series.