Welcome to Doom9's Forum, THE in-place to be for everyone interested in DVD conversion. Before you start posting please read the forum rules. By posting to this forum you agree to abide by the rules. |
|
|
Thread Tools | Search this Thread | Display Modes |
5th March 2018, 23:42 | #41 | Link |
Registered User
Join Date: Feb 2002
Location: San Jose, California
Posts: 4,406
|
At those prices buying a Titian V would seem a better investment.
__________________
madVR options explained |
21st March 2018, 20:42 | #42 | Link |
Registered User
Join Date: Oct 2001
Location: Germany
Posts: 7,259
|
may be buying a Titan V wouldn't be such a good idea,... http://www.theregister.co.uk/2018/03...producibility/
|
2nd September 2018, 07:02 | #43 | Link |
Registered User
Join Date: Nov 2006
Posts: 90
|
Sorry, may be not correct to post in this thread.
But found fresh commercial release of Topaz A.I. Megascale. And looks like it finally that can be named modern A.I. upscale, that ready for consumers. SRC 200% no enchance 400% with enchance https://i.imgur.com/PoEIzan.jpg SRC 200% no enchance 400% with enchance https://i.imgur.com/Zd6EMVa.jpg SRC 200% no enchance 400% with enchance https://i.imgur.com/gVJa87X.jpg SRC 200% no enchance 400% with enchance https://i.imgur.com/3I2A99w.jpg Good that it quite fast and have batch support. Bad (may be) that this it work only with RGB. |
2nd September 2018, 17:24 | #44 | Link |
Registered Developer
Join Date: Sep 2006
Posts: 9,140
|
It looks very nicely detailed and has a high-res look, but whether or not it has the same problems (e.g. create "ghost" images where the neural network paints distorted faces where they shouldn't be etc) like other SRGAN neural networks we don't know for sure. Furthermore, in the baby face, look at the eye lashes of the left eye. *Heavy* ringing artifacts there!
|
2nd September 2018, 21:28 | #46 | Link | |
Registered User
Join Date: Feb 2002
Location: California
Posts: 2,691
|
Quote:
|
|
3rd September 2018, 02:45 | #48 | Link |
Registered User
Join Date: Nov 2006
Posts: 90
|
I guess that enhance mean some presharpen and some denoise.
With videos... well it have batch mode. just drag and drop and start. More question about temporal stability for videos. And not least colors (as i see it work only with RGB) |
3rd September 2018, 02:50 | #49 | Link |
Registered User
Join Date: Nov 2006
Posts: 90
|
Comparing to other upscalers. I think this one can be used for some video works. But it will required prefiltering (especially for DVD sources) and post filterings (like dehalo,"smart" sharpen, etc.) to rich best results.
So this is not "one click" Solution. but it looks more ready than most of "proof of concepts" on web. Because already have prebuild binaries (with not a bad UI) already optimized for memory (you can upscale 4K to 8K) etc. |
10th September 2018, 18:16 | #51 | Link |
Registered User
Join Date: Sep 2007
Posts: 5,346
|
sort of related and on topic - WolframRhodium has a bunch of pre trained models that can be used in vapoursynth with mxnet
https://github.com/WolframRhodium/Super-Resolution-Zoo https://github.com/WolframRhodium/mu...tion_mxnet.vpy nice to see implementations of various research papers |
10th September 2018, 19:07 | #52 | Link |
Registered User
Join Date: Jan 2016
Posts: 162
|
Those models are not implemented or even trained by me. I simply convert the models provided by the authors of academic papers or other algorithm engineers that are implemented in other deep learning framework to MXNet. You should attribute the main contribution to them rather than me.
|
10th September 2018, 19:14 | #53 | Link | |
Registered User
Join Date: Sep 2007
Posts: 5,346
|
Quote:
But thanks for converting them to for MXNet compatibility. It's nice to be able to actually test some of these things out. It's extremely difficult to use some of the algorithms outlined in the various papers for typical users |
|
Thread Tools | Search this Thread |
Display Modes | |
|
|