AI-based upsampling tech creates high-res versions of low-res images
[Philip Lelyveld summary: the AI identifies each object, searches the web for related higher-resolution images, then adds realistic textures to the up-res'd pixelated image.]
The team has developed a tool called EnhanceNet-PAT, which is capable of creating high-definition versions of low-resolution images, using artificial intelligence.
We take a different approach by instead asking the neural network to produce realistic textures. To do this, the neural network takes a look at the whole image, detects regions, and uses this semantic information to produce realistic textures and sharper images.”
To train the technology, large image libraries were fed into the AI-based system to accumulate knowledge of textures. The neural network is then given the task of upsampling previously downsized images. Finally, the research team compares the results to the original high-resolution image and modifies the algorithm to correct for errors or inconsistencies—this way, the algorithm keeps improving and after some time can work without any human help.
To learn more about this technology, check out the full research paper here.
See the full article here: https://www.dpreview.com/news/2842585992/researchers-teach-algorithm-about-textures-to-create-high-res-versions-of-low-res-images