Re:Creating photorealistic images with neural networks and a...
by sharemywin on Friday February 17, 2017 @12:12PM
(#13669865)
How fast does it take to run? could it be done in real time for compression? Also, wonder how low of resolution you could go?
[ Parent
| on HN ]
Re:Creating photorealistic images with neural networks and a...
by dewitt on Friday February 17, 2017 @12:38PM
(#13670101)
Yes, it can be used for image compression:
https://research.googleblog.com/2016/09/image-compression-wi...
Here's the paper:
https://arxiv.org/abs/1608.05148
(No connection to the authors, just found it super cool when I read it a few months back.)
Re:Creating photorealistic images with neural networks and a...
by simcop2387 on Friday February 17, 2017 @05:33PM
(#13672312)
I wish they would have compared a JPEG with quality reduced to match the filesize of their NN compressed image. It'd be useful to compare what artifacts are introduced and seeing just how much better it does for the same size.
Re:Creating photorealistic images with neural networks and a...
by curuinor on Friday February 17, 2017 @12:45PM
(#13670154)
Any and every machine learning algorithm can be used for compression. Most ConvNet shit cannot be run in true real time in any way shape or form even with GPU: latencies are on the order of 500ms-1sec, so noticeable even if you have more datacenters than God, like Google does.