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.

 

Go Back   Doom9's Forum > Announcements and Chat > General Discussion

Reply
 
Thread Tools Search this Thread Display Modes
Old 5th March 2018, 23:42   #41  |  Link
Asmodian
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
Asmodian is offline   Reply With Quote
Old 21st March 2018, 20:42   #42  |  Link
Selur
Registered User
 
Selur's Avatar
 
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/
__________________
Hybrid here in the forum, homepage
Selur is offline   Reply With Quote
Old 2nd September 2018, 07:02   #43  |  Link
SSH4
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.
SSH4 is offline   Reply With Quote
Old 2nd September 2018, 17:24   #44  |  Link
madshi
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!
madshi is offline   Reply With Quote
Old 2nd September 2018, 19:26   #45  |  Link
wonkey_monkey
Formerly davidh*****
 
wonkey_monkey's Avatar
 
Join Date: Jan 2004
Posts: 2,493
And the real question is: how well does it work with video?
__________________
My AviSynth filters / I'm the Doctor
wonkey_monkey is offline   Reply With Quote
Old 2nd September 2018, 21:28   #46  |  Link
johnmeyer
Registered User
 
Join Date: Feb 2002
Location: California
Posts: 2,691
Quote:
Originally Posted by madshi View Post
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!
I see ringing on the 200% pic in his right eye (his right, our left), but do NOT see those artifacts in the 400% version posted on Imgur. The 400% has "enhancement" and the 200% does not. However, I have no idea what enhancement is being applied and whether that would reduce ringing.
johnmeyer is offline   Reply With Quote
Old 2nd September 2018, 23:05   #47  |  Link
wonkey_monkey
Formerly davidh*****
 
wonkey_monkey's Avatar
 
Join Date: Jan 2004
Posts: 2,493
For what it's worth, here is the baby's eye from the 200% version (left) compared with the 400% version scaled down:



400% version is a lot cleaner and has a lot fewer JPEG artefacts (over the whole image).
__________________
My AviSynth filters / I'm the Doctor
wonkey_monkey is offline   Reply With Quote
Old 3rd September 2018, 02:45   #48  |  Link
SSH4
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)
SSH4 is offline   Reply With Quote
Old 3rd September 2018, 02:50   #49  |  Link
SSH4
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.
SSH4 is offline   Reply With Quote
Old 9th September 2018, 19:32   #50  |  Link
foxyshadis
ангел смерти
 
foxyshadis's Avatar
 
Join Date: Nov 2004
Location: Lost
Posts: 9,558
Katie-derailment has been moved out to its own thread.
foxyshadis is offline   Reply With Quote
Old 10th September 2018, 18:16   #51  |  Link
poisondeathray
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
poisondeathray is offline   Reply With Quote
Old 10th September 2018, 19:07   #52  |  Link
WolframRhodium
Registered User
 
Join Date: Jan 2016
Posts: 162
Quote:
Originally Posted by poisondeathray View Post
sort of related and on topic - WolframRhodium has a bunch of pre trained models that can be used in vapoursynth with mxnet

nice to see implementations of various research papers
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.
WolframRhodium is offline   Reply With Quote
Old 10th September 2018, 19:14   #53  |  Link
poisondeathray
Registered User
 
Join Date: Sep 2007
Posts: 5,346
Quote:
Originally Posted by WolframRhodium View Post
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.
Right, sorry bad phrasing .

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
poisondeathray is offline   Reply With Quote
Old 10th September 2018, 21:08   #54  |  Link
Wilbert
Moderator
 
Join Date: Nov 2001
Location: Netherlands
Posts: 6,364
Quote:
Originally Posted by foxyshadis View Post
Katie-derailment has been moved out to its own thread.
I removed them and restored his/her other thread.
Wilbert is offline   Reply With Quote
Old 11th September 2018, 01:11   #55  |  Link
WolframRhodium
Registered User
 
Join Date: Jan 2016
Posts: 162
Quote:
Originally Posted by poisondeathray View Post
Right, sorry bad phrasing .

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
Yes, some algorithms are more inclined to be benchmarks rather than for actual use. Just use the other efficient ones.
WolframRhodium is offline   Reply With Quote
Reply

Thread Tools Search this Thread
Search this Thread:

Advanced Search
Display Modes

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off

Forum Jump


All times are GMT +1. The time now is 22:46.


Powered by vBulletin® Version 3.8.11
Copyright ©2000 - 2024, vBulletin Solutions Inc.