Non-Regularized Direct Superresolusion for Realistic Image ReconstructionTechnology #ua15-201
Questions about this technology? Ask a Technology Manager
- Jeffrey Rodriguez Associate Professor, Electrical & Computer Engineering
- Rongguang Liang Professor, Optical Sciences
- Basel Salahieh Graduate Associate, Optical Sciences
- Managed By
- Amy Phillips Sr. Licensing Manager (520) 621-9579
Summary: Researchers at the University of Arizona have developed a super-resolution (SR) technique that creates sharper images from low-quality or small cameras without fabricating the details. The novel technique applies motion to multiple images and then uses a non-regularized algorithm that directly solves a fully-characterized multi-shift imaging system to grant realistic restorations with physically accurate high resolution.
Background: Currently known SR techniques employ optimized priors and regularizers to deliver stable appealing restorations even though they deviate from physically accurate reconstructions. The popular inversion process creates detail that is not necessarily true, with ambiguous solution sets.
* converts low-resolution images to high resolution without untrue artifacts
* can work with any digital camera
* medical imaging
Status: Provisional Patent Application filed
Contact: Amy Phillips; firstname.lastname@example.org
Refer to case number UA15-201
Inventors: Basel Salahieh and Rongguang Liang