{"id":565,"date":"2020-11-11T11:06:14","date_gmt":"2020-11-11T11:06:14","guid":{"rendered":"https:\/\/blog.comixify.ai\/?p=565"},"modified":"2020-11-12T10:32:36","modified_gmt":"2020-11-12T10:32:36","slug":"comixify-with-a-new-super-resolution-model","status":"publish","type":"post","link":"https:\/\/blog.comixify.ai\/index.php\/2020\/11\/11\/comixify-with-a-new-super-resolution-model\/","title":{"rendered":"Comixify with a new Super Resolution model!"},"content":{"rendered":"Read-o-Meter<\/span> 2<\/span> minutes<\/span><\/span>\n
VFX platform now with Super Resolution!<\/strong><\/h5>\n\n\n\n
\"\"<\/figure><\/div>\n\n\n\n

by Maciej P\u0119\u015bko<\/a><\/p>\n\n\n\n

<\/p>\n\n\n\n

It has been a while but we are pleased to announce that Comixify VFX Platform has been extended with an additional module. Please welcome Super Resolution! This new functionality is now available for free for all the beta testing users (If you are not one of them, you can still apply for a free<\/strong> beta testing account under this link<\/a>). <\/p>\n\n\n\n

\"\"<\/a>
Comixify VFX SaaS Platform <\/figcaption><\/figure>\n\n\n\n\n\n\n\n

<\/p>\n\n\n\n

What exactly hides under the mysterious \u2018Super Resolution\u2019 name? Well, let\u2019s imagine one has plenty of low-resolution video sequences like 480p or 720p. Such scenes often cannot be used during video production because standards are 4K and 8K. What can one do with this fact? Obviously, the first idea is to use a simple upscaling algorithm with bicubic, linear or nearest-neighbor interpolation. Unfortunately, no additional information will be added then. In other words, an upscaled video would still have the same amount of details, the only thing that would change is the number of pixels in each frame. Clearly, that is not the desired outcome…<\/p>\n\n\n\n

Luckily, our Super Resolution module can help with that, because it works in a completely different way. The Deep Learning model behind our service is trained to understand the content of the provided video in order to enhance the details frame by frame across the whole sequence. It was trained on the huge dataset of different video scenes to make it as versatile as possible hereby it allows one to upsample any video sequence up to 8K with an increasing level of details. <\/p>\n\n\n\n

\n