Amazon Rekognition: Dealing With An Asset Library 1000x Faster
Subscribe:  iCal  |  Google Calendar
San Antonio US   18, Jan — 21, Jan
London GB   21, Jan — 23, Jan
Taipei TW   24, Jan — 29, Jan
Zürich CH   31, Jan — 4, Feb
Leamington Spa GB   31, Jan — 3, Feb
Latest comments
by Frank
6 hours ago

Is there any way i can tweak the colors dynamically through another blueprint? I tried with the "get all actors of class" function and setting the colors of the clouds by a timeline, everything else connected to the timeline does its thing but the volumetric clouds wouldn't change. Are the properties somehow fix?

by Ronnie Ochero
9 hours ago

Hi, what version of blender does this work with?

by anonymous
14 hours ago

Yeah this is good but it doenst capture the 2d look it still looks 3d. How about copying the movement of 2d animation because this looks way too smooth. 1 example is using the classic by twos which most studios do or also use 24 fps to really capture the 2d feel

Amazon Rekognition: Dealing With An Asset Library 1000x Faster
20 September, 2018

Finding related textures in a texture library can be a difficult task, but here’s something from Amazon that can help you. Amazon Rekognition, the team’s machine learning API, will allow you to tag your textures and do searches to find specific ones in seconds.

You probably have a large asset library of textures or scenes that is your “painter’s palette”. This palette is crucial when it comes to bringing your scenes to life, but there are some problems when searching for the right files, right? 

The files are not always tagged correctly, so your folders and filenames might be misleading or partially correct. Tagging all the files by hand is not a bright idea, not even a realistic one. 

Amazon Rekognition, Amazon’s image recognition that utilizes machine learning, turns a manual process into a simple and exponentially faster one. “By comparison, if an artist took 40 seconds to open a file, look at the image, form an opinion, and write multiple tags to it, then store in a database, it would take them about over 55 working hours to process 5,000 files. By comparison, this can be batched and completed in the time it takes to upload the images using Rekognition,” explained the team. Uploading at a speed of 200 megabits per second, it takes a little less than 3 minutes to complete with a new toolkit.

You can learn more and get started here

Leave a Reply

Be the First to Comment!

Related articles
Environment Art Program
Character Art Program