RPI ID:
2023-075-301

Innovation Summary:
This technology introduces systems and methods for synthesizing image data using super-resolution (SR) techniques. It leverages multiple low-resolution (LR) images to generate high-resolution (HR) outputs by extracting and combining fine-grained features across frames. The system is designed to enhance image quality in scenarios where high-resolution acquisition is limited or impractical. It supports applications in medical imaging, remote sensing, and surveillance where clarity and detail are critical.

Challenges / Opportunities:
High-resolution imaging often requires expensive hardware or prolonged acquisition times. This invention addresses the challenge by enabling HR synthesis from existing LR datasets, reducing cost and exposure time. It opens opportunities for improved diagnostics, enhanced visual analytics, and more efficient data storage. The method also supports training AI models with enriched image datasets.

Key Benefits / Advantages:
✔ Synthesizes high-resolution images from low-resolution inputs
✔ Reduces hardware and acquisition costs
✔ Enhances image clarity and detail
✔ Applicable across multiple imaging domains

Applications:
• Medical imaging, remote sensing, surveillance, and AI model training

Keywords:
Image synthesis, super-resolution, low-resolution imaging, high-resolution reconstruction, visual analytics

Intellectual Property:
WO2024249830A2 (Application PCT/US2024/031962), Published May 31, 2024