Super-resolution is a mathematical algorithm that combines multiple low-resolution input images and creates one image of higher resolution. We provide an efficient implementation that runs in mobile devices equipped with digital cameras. The Android application is available. You can download a demo application (tested on Nexus 5), which performs SR.
Algorithm:
| 1) Acquire multiple images in a burst mode | 2) Registration with subpixel accuracy | 3) Interpolation on high-resolution grid | 4) Deconvolution of the high-res. image |
|
|
|
|
How super-resolution goes beyond the standard camera resolution?
 |
Input image |
 |
Super-resolution from 5 images |
 |
Super_resolution from 10 images |
Supplementary material: demo video
You can download a demo application (tested on Nexus 5), which performs SR on the central region of photos.
More examples:
Move the slider to see the restored images. Notice that not only noise is removed but also small details are restored, which is the result of super-resolution. The examples in full resolution are available here.
| JPEG output of the camera. |
 |
| Details: | funded by Artemis No. 621439, "Almarvi" and GACR No. GA13-29225S |
| Duration: | 2014-2017 |
| Contact person: | Filip Sroubek |
| Involved people: | Barbara Zitova, Jan Kamenický, Ondřej Šindelář |
Publications:
|
Image Restoration in Portable Devices: Algorithms and Optimization |
|
 |
Algorithms, Design Methods, and Many-Core Execution Platform for Low-Power Massive Data-Rate Video and Image Processing Artemis No. 621439 |
