AI-based upsampling tech creates high-res versions of low-res images: Digital Photography Review

https://m.dpreview.com/news/2842585992/researchers-teach-algorithm-about-textures-to-create-high-res-versions-of-low-res-images

Upsampling image and video files usually leads to pixelation and soft textures, simply because algorithms are not capable of replacing non-existing image detail. But scientists at the Max-Planck Institute for Intelligent Systems in Germany have come up with a clever solution that is capable of producing better results than anything we’ve seen so far.

1 Comment

  1. Tomi Engdahl says:

    Gfycat wants to fix your low-fidelity GIFs with machine learning
    https://techcrunch.com/2017/12/13/gfycat-wants-to-fix-your-low-fidelity-gifs-with-machine-learning/?ncid=rss&utm_source=tcfbpage&utm_medium=feed&utm_campaign=Feed%3A+Techcrunch+%28TechCrunch%29&utm_content=FaceBook&sr_share=facebook

    Gfycat is now making a big push on the technical front to make those GIFs look better and more discoverable as creators look to continue to upload content, regardless of what kind of quality or fidelity they are. And it’s more of a video problem than an image recognition problem, CEO Richard Rabbat said.

    https://gfycat.com

    Reply

Leave a Comment

Your email address will not be published. Required fields are marked *

*

*