Researchers from NJU and PKU have developed a lensless imaging method using deep learning that reconstructs high-fidelity dynamic images from single shots.
Key Details
- 1New 'McLDI-INR' framework integrates physical models with implicit neural representation for lensless imaging.
- 2Overcomes traditional need for multiple acquisitions and strong priors in dynamic (moving) imaging scenarios.
- 3Uses a binary mask and dual-domain loss (spatial and frequency) to improve image quality and reduce motion blur.
- 4Demonstrated improved reconstruction of moving objects (including biological samples) in both simulation and real-world experiments.
- 5Published in Intelligent Opto-Electronics, June 2026; supported by multiple Chinese science foundations.
Why It Matters
This approach could enable more compact and practical imaging systems, particularly benefiting portable microscopy, dynamic biological observation, and potentially point-of-care medical diagnostics. High-resolution single-shot reconstruction of moving targets is a longstanding challenge, making this advance significant for next-generation imaging AI and device design.
Source
EurekAlert
Related News
•EurekAlert
TRUECAM AI Framework Boosts Reliability in Cancer Pathology Imaging
PolyU researchers introduce the TRUECAM AI framework to enhance the trustworthiness of pathology AI for cancer diagnosis.
•EurekAlert
Deep Learning Shows Superior Sensitivity in Sinus Disease CT Changes
Automated deep learning achieves greater sensitivity in detecting treatment-related changes in chronic sinus disease on CT scans than standard visual scoring.
•EurekAlert
Mayo Clinic's AI Advances Ultrasound Detection of Heart Obstruction
Mayo Clinic researchers have developed an AI model that detects heart obstructions from routine ultrasound, potentially improving early identification of at-risk patients.