News for hackers. Stuff that matters.
Re:With Google's RAISR, images can be up to 75% smaller with... by wodenokoto on Monday January 16, 2017 @03:32PM (#13412761)
The article makes it sound like it is some sort of machine learning algorithm, which makes me wonder: How is the upscaling done client side?
Re:With Google's RAISR, images can be up to 75% smaller with... by sushisource on Monday January 16, 2017 @03:42PM (#13412826)
It's very much within the realm of possibility to have a pre-trained neural net on the client, which then simply asks it questions.

For example, swiftkey does this already with its keyboard prediction. Prisma does it with image styling.

Re:With Google's RAISR, images can be up to 75% smaller with... by gkbrk on Monday January 16, 2017 @05:50PM (#13413733)
I actually think Prisma sends the image to their servers for processing, their app size is way too small to contain that many trained networks. Also it doesn't work without an internet connection if I'm correct.
Re:With Google's RAISR, images can be up to 75% smaller with... by HisGraceTheDuck on Monday January 16, 2017 @06:54PM (#13414126)
That used to be the case but recent updates do the processing on the device now. I don't know how they managed it but they did.
Re:With Google's RAISR, images can be up to 75% smaller with... by wodenokoto on Tuesday January 17, 2017 @07:43AM (#13416962)
It is possible, no doubt. You also have image decoder on the client and getting support for a new format is difficult because it is the browser vendors job to distribute these.

So how do they practically get the client to decode / upscale? JavaScript?