10-2010-2370 | Fast Image and Video Upscaling from Self-Examples
Raanan Fattal, HUJI, School of Computer Science and Engineering Gilad Freedman, HUJI, School of Computer Science and Engineering
Preserves sharp edges in enlarged images
|
Categories
|
Image processing, Video processing
|
|
Development Stage
|
Development completed
|
|
Patent Status
|
Provisional patent submitted
|
|
Market
|
Image enhancement software market
|
Highlights
-
Image upscaling, or enlargement of image size, results in blurring of edges and loss of image quality
-
Although digital cameras produce high-resolution images, there still exist huge numbers of low resolution images as well as low-grade sensors found in mobile devices and surveillance systems that produce low-resolution images and video frames that require resolution enhancement.
Our Innovation
New image processing algorithm based on example-based super-resolution that results in a high-quality and efficient single-image upscaling technique
Image upsampling exploits local scale-similarity in natural images. When downscaled, the patches (yellow squares) are very similar to their cropped version (red squares).
Image upsampling exploits local scale-similarity in natural images. When downscaled, the patches (yellow squares) are very similar to their cropped version (red squares).
Key Features
-
Algorithm produces high-quality, sharp images
-
Reduces the process search time without compromising quality
-
Simple, efficient, and trivially parallel algorithm enables increase in the resolution of video sequences with no algorithmic modifications and at reasonable running times
Development Milestones
Seeking licensing agreements with image processing and editing software developers
The Opportunity
Can be employed with any image editing software as well as software for adapting videos to new HD standards
Contact for more information:
Tamir Huberman  , Licensing Officer Computer Science & IT Director, +972-2-6586678
|
