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 > Capturing and Editing Video > NLE - Non Linear Editing

Reply
 
Thread Tools Search this Thread Display Modes
Old 12th August 2021, 01:41   #1  |  Link
takla
Registered User
 
Join Date: May 2018
Posts: 182
Topaz Video Enhance AI

https://topazlabs.com/downloads/

Thoughts on this neat piece of software?

Personally, I think it outperforms all deblock/deblur/degrain and sharpening tools from avisynth/vapoursynth by a landslide.

Some benchmark:
Artemis High Quality v12 (1080p > 2160p) takes around 0.55 seconds per frame on my AMD RX 5700.

It is rather slow, but for the quality you get it is unmatched.

I also think all models but Artemis are redundant, because not only do they cause some artefacts (which artemis does not), they also are much slower (up to twice as slow). And just in general, scaling higher then 200% is pointtless.
takla is offline   Reply With Quote
Old 13th August 2021, 23:26   #2  |  Link
lansing
Registered User
 
Join Date: Sep 2006
Posts: 1,657
For anime probably yes. But for live action, it'll be a hit or miss, with miss most of the time. And that processing time is just impractical. I'm not wasting a month just to upscale an one hour video, you are crazy.
lansing is offline   Reply With Quote
Old 14th August 2021, 00:48   #3  |  Link
Zarxrax
Registered User
 
Join Date: Dec 2001
Posts: 1,219
Haven't tried Video Enhance AI, but VSGAN for vapoursynth is basically the same thing, and there are lots of great user-generated models that can work with it.
Zarxrax is offline   Reply With Quote
Old 14th August 2021, 04:02   #4  |  Link
takla
Registered User
 
Join Date: May 2018
Posts: 182
Quote:
Originally Posted by lansing View Post
For anime probably yes. But for live action, it'll be a hit or miss, with miss most of the time. And that processing time is just impractical. I'm not wasting a month just to upscale an one hour video, you are crazy.
<0.6 sec per frame is slightly less then 13h for 20 minutes of 1080p to 2160p (sd 540p to 1080p is 0.1sec per frame, very doable). And that speed is with a midrange gpu from 2019. You can expect that time to be cut in half with the next generation of gpus.

Quote:
Originally Posted by Zarxrax View Post
Haven't tried Video Enhance AI, but VSGAN for vapoursynth is basically the same thing, and there are lots of great user-generated models that can work with it.
esrgan and vsgan are cuda based, which means they only work on nvidia gpus. so not possible for me to test. Edit: in the vsgan thread someone posted it takes around 1.4sec per frame. that is much longer then topaz, but depending on the model might work out much better.

Last edited by takla; 14th August 2021 at 04:19.
takla is offline   Reply With Quote
Old 14th August 2021, 13:42   #5  |  Link
Zarxrax
Registered User
 
Join Date: Dec 2001
Posts: 1,219
Quote:
Originally Posted by takla View Post
esrgan and vsgan are cuda based, which means they only work on nvidia gpus. so not possible for me to test. Edit: in the vsgan thread someone posted it takes around 1.4sec per frame. that is much longer then topaz, but depending on the model might work out much better.
Yeah, its highly dependent on the model. Depending on the model I'm using, I have seen differences of more than 5x in the encoding time. Even with the fastest models, its still quite slow.
Zarxrax is offline   Reply With Quote
Old 15th August 2021, 04:32   #6  |  Link
kedautinh12
Registered User
 
Join Date: Jan 2018
Posts: 2,153
Waiting for avs port of vsgan

Last edited by kedautinh12; 15th August 2021 at 04:38.
kedautinh12 is offline   Reply With Quote
Old 20th August 2021, 11:08   #7  |  Link
lollo2
Registered User
 
lollo2's Avatar
 
Join Date: Aug 2017
Location: Italy
Posts: 113
Quote:
Personally, I think it outperforms all deblock/deblur/degrain and sharpening tools from avisynth/vapoursynth by a landslide.
Personally, on my s-vhs captures I experimented that it is not any better than a full AviSynth restoration + upscale flow:

https://forum.videohelp.com/threads/...ts#post2620598

https://forum.videohelp.com/threads/...e9#post2626723

I used it just as an upscaler after the excellent avisynth denoise + sharpening, so Topaz VEAI takes advantage of the avisynth restoration; otherwise in my case is not even worth of consideration!

Last edited by lollo2; 20th August 2021 at 11:17.
lollo2 is offline   Reply With Quote
Old 20th August 2021, 11:44   #8  |  Link
PatchWorKs
Registered User
 
PatchWorKs's Avatar
 
Join Date: Aug 2002
Location: Italy
Posts: 303
I repost the question here:

Hi there, I recently found this Upscale "render" that has an interesting workflow:
Quote:
Flowframes (framerate interpolation): https://nmkd.itch.io/flowframes
Topaz Video AI (resolution upscale): https://www.topazlabs.com/video-enhance-ai
Transition Chooser to clean up scene changes and artifacting: https://www.magentacloud.de/share/lg6gou41fc
Judge result yourself:
https://www.youtube.com/watch?v=iUPVczZ2Xq4

...how to implement it with open source softwares only ?

Hope that helps/inspires.
PatchWorKs is offline   Reply With Quote
Old 20th August 2021, 11:58   #9  |  Link
kedautinh12
Registered User
 
Join Date: Jan 2018
Posts: 2,153
Quote:
Originally Posted by lollo2 View Post
Personally, on my s-vhs captures I experimented that it is not any better than a full AviSynth restoration + upscale flow:

https://forum.videohelp.com/threads/...ts#post2620598

https://forum.videohelp.com/threads/...e9#post2626723

I used it just as an upscaler after the excellent avisynth denoise + sharpening, so Topaz VEAI takes advantage of the avisynth restoration; otherwise in my case is not even worth of consideration!
Are you sure it's better VSGAN??
https://rlaphoenix.github.io/VSGAN/
kedautinh12 is offline   Reply With Quote
Old 20th August 2021, 13:01   #10  |  Link
lollo2
Registered User
 
lollo2's Avatar
 
Join Date: Aug 2017
Location: Italy
Posts: 113
I don’t know yet. Selur addressed me to some AI filters in VapourSynth, but I still have to try (TecoGAN should be the best candidate).

In any case, he seems to indicate that the VapourSynth AI model approach is better than Topaz VEAI (and in my case I am sure it is )

Last edited by lollo2; 20th August 2021 at 13:37.
lollo2 is offline   Reply With Quote
Old 20th August 2021, 13:29   #11  |  Link
lollo2
Registered User
 
lollo2's Avatar
 
Join Date: Aug 2017
Location: Italy
Posts: 113
Quote:
Originally Posted by PatchWorKs View Post
I repost the question here:
You already had the answer: https://forum.videohelp.com/threads/...11#post2627997

Are you looking for something different?

Last edited by lollo2; 20th August 2021 at 13:38.
lollo2 is offline   Reply With Quote
Old 20th August 2021, 20:54   #12  |  Link
Selur
Registered User
 
Selur's Avatar
 
Join Date: Oct 2001
Location: Germany
Posts: 7,259
side note: In theory TecoGan, iSeeBetter (and probably Topaz Video Enhance AI) are mainly interessting since they are designed to look at video and not single images and thus might produce better results since they also look at the adjustend frames and not a single frame.
Some folks first filter with Vapoursynth and then use Topaz Video Enhance AI, TecoGan, iSeeBetter in the hope to get a better results.

That said at least for Topaz Video Enhance AI on it's own I haven't seen anything so far that one couldn't archive or beat with Vapoursynth or Avisynth.

Problem with all the ML/AI stuff is simply the lack or control and ability to fine tune, Topaz tries to lessen this by:
a. providing different models
b. updating their models.
-> All this would be way more interessting if current graphic cards weren't so damn expensive. (and thus at least for me, who isn't earning money with it, it simply is not worth it)

Cu Selur
__________________
Hybrid here in the forum, homepage
Selur is offline   Reply With Quote
Old 20th August 2021, 21:09   #13  |  Link
lollo2
Registered User
 
lollo2's Avatar
 
Join Date: Aug 2017
Location: Italy
Posts: 113
Quote:
That said at least for Topaz Video Enhance AI on it's own I haven't seen anything so far that one couldn't archive or beat with Vapoursynth or Avisynth.
I agree, as everybody who seriously tried both
lollo2 is offline   Reply With Quote
Old 21st August 2021, 18:31   #14  |  Link
takla
Registered User
 
Join Date: May 2018
Posts: 182
Quote:
Originally Posted by lollo2 View Post
Personally, on my s-vhs captures I experimented that it is not any better than a full AviSynth restoration + upscale flow:

https://forum.videohelp.com/threads/...ts#post2620598

https://forum.videohelp.com/threads/...e9#post2626723

I used it just as an upscaler after the excellent avisynth denoise + sharpening, so Topaz VEAI takes advantage of the avisynth restoration; otherwise in my case is not even worth of consideration!
As I already said, people should use Artemis because it is the fasted and most tuned model. Furthermore, all AI models do denoising, so denoising with avisynth is pointless (will destroy too much fine detail if denoised twice). The same is true for sharpening (as long as your source is not too soft). Both of these things Artemis can do much better.

And personally, I'd save topaz output to prores (and use ffmpeg with more control for final encode)

Oh and for interlaced content I use bwdif because qtgmc makes the image look like a waxpainting.

Last edited by takla; 21st August 2021 at 18:48.
takla is offline   Reply With Quote
Old 21st August 2021, 18:53   #15  |  Link
takla
Registered User
 
Join Date: May 2018
Posts: 182
Quote:
Originally Posted by PatchWorKs View Post
I repost the question here:

Hi there, I recently found this Upscale "render" that has an interesting workflow:


Judge result yourself:
https://www.youtube.com/watch?v=iUPVczZ2Xq4

...how to implement it with open source softwares only ?

Hope that helps/inspires.
Your youtube video is in 24 fps...
takla is offline   Reply With Quote
Old 21st August 2021, 21:05   #16  |  Link
lollo2
Registered User
 
lollo2's Avatar
 
Join Date: Aug 2017
Location: Italy
Posts: 113
Quote:
As I already said, people should use Artemis because it is the fasted and most tuned model. Furthermore, all AI models do denoising, so denoising with avisynth is pointless (will destroy too much fine detail if denoised twice). The same is true for sharpening (as long as your source is not too soft). Both of these things Artemis can do much better.
As I already said, in my experiments Topaz VEAI is far inferior to AviSynth processing for denoising and sharpening. I gave it a second chance as an upscaler, it failed as well to improve over my AviSynth flow. In my case Topaz VEAI is useless (I posted some comparison and some restoration work in the posts I linked), but YMMV and, of course, every opinion is respectable ;-)
lollo2 is offline   Reply With Quote
Old 22nd August 2021, 01:12   #17  |  Link
kedautinh12
Registered User
 
Join Date: Jan 2018
Posts: 2,153
Quote:
Originally Posted by takla View Post
Furthermore, all AI models do denoising, so denoising with avisynth is pointless (will destroy too much fine detail if denoised twice).
I think you still don't use KNLMeansCL and BM3D. Two denoiser is very good and don't detroy too much fine detail. It's still low but if you use GPU ver, it will faster
kedautinh12 is offline   Reply With Quote
Old 22nd August 2021, 09:16   #18  |  Link
takla
Registered User
 
Join Date: May 2018
Posts: 182
Quote:
Originally Posted by kedautinh12 View Post
I think you still don't use KNLMeansCL and BM3D. Two denoiser is very good and don't detroy too much fine detail. It's still low but if you use GPU ver, it will faster
I never got knlmeansCL to work on my gpu, and bm3d uses cuda, so it only works with a nvidia gpu, so I cannot test it. And for the cpu version of nlmeans, quality-to-speed ratio is inferior to what I can achieve with mvtools2 (I posted my denoise script in the mvtools2 thread) still, it is inferior to what I achieve with topaz.

Last edited by takla; 22nd August 2021 at 09:24.
takla is offline   Reply With Quote
Old 22nd August 2021, 10:51   #19  |  Link
kedautinh12
Registered User
 
Join Date: Jan 2018
Posts: 2,153
Bm3d have cpu ver. If you have cpu with many core, you will use prefetch() and got fast fps too
https://github.com/WolframRhodium/Va...ment-886173346
kedautinh12 is offline   Reply With Quote
Old 22nd August 2021, 11:24   #20  |  Link
takla
Registered User
 
Join Date: May 2018
Posts: 182
Here are some comparison between: Raw (Original + Spline36), MDegrain (Spline36 + Adaptive Sharpen), Topaz AI (Artemis High Quality v12)

MDegrain uses Delta=4, thSAD=150, blksize=16 & overlap=8.

https://drive.google.com/drive/folde...j_WGZd6JwxYUoH

Last edited by takla; 22nd August 2021 at 11:37.
takla is offline   Reply With Quote
Reply

Tags
topaz, topaz ai, upscale

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 17:11.


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