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. |
29th May 2020, 22:39 | #482 | Link | |
Registered User
Join Date: Dec 2002
Location: Region 0
Posts: 1,436
|
Quote:
I'd argue it's best to only scale it once instead in of multiple steps. |
|
30th May 2020, 18:05 | #483 | Link | |
Registered User
Join Date: Oct 2001
Posts: 454
|
Quote:
BTW, they released a new beta with a new model yesterday. |
|
30th May 2020, 19:29 | #485 | Link |
Registered User
Join Date: May 2020
Posts: 77
|
John,
For decades, the idea of "Enhance" -- as in, the recovery of detail levels over and above what was originally encoded in the source -- was a joke. Completely farcical. You're not wrong. AI-based upscalers have turned science fiction into reality. There are different models that process the final image in different ways. Topaz Video Enhance AI is very much a work in progress. If you want to see an example of the same video scene run through an upscaler without using YouTube as an intermediary, here: This link is to samples Hello_Hello provided of some DVD clips I gave him: https://www.sendspace.com/file/gwxxi0 This link is where you can download upscaled versions of those samples: https://www.sendspace.com/filegroup/...8pntkJJg0KsgtR The SFE-1 and SFE-2 videos are upscaled using two different models -- Gaia-CG and Gaia-HQ, both available in Topaz Video Enhance AI. You can see the significant level of improvement for yourself. You may not like it, of course, but you will not fail to see the difference. |
30th May 2020, 21:01 | #486 | Link |
Registered User
Join Date: Dec 2002
Location: Region 0
Posts: 1,436
|
I mean mean taking the output from Topaz and getting it into 2880x2160 YUV420. 444 to 420 requires scaling the chroma. You've also got to turn 3840x2160 into 2880x2160. It's probably best to do that in only 1 operation instead of compounding multiple separate steps that each can degrade the image.
|
30th May 2020, 21:18 | #487 | Link | |
Registered User
Join Date: May 2020
Location: Canada
Posts: 49
|
Quote:
Code:
#outfolder is the topaz output directory, filecnt is # of images ImageSource(file=outfolder+"\%06d.tiff",start=0,end=FileCnt-1,fps=23.976,pixel_type="RGB48") ConvertToPlanarRGB() z_ConvertFormat(width=2880, height=2160, resample_filter="bicubic",pixel_type="YUV420P16", colorspace_op="rgb:srgb:170m:f=>709:709:709:f") TemporalDegrain2(grainLevel=false) neo_f3kdb(range=31, grainY=15, grainC=10, sample_mode=2, dither_algo=3, dynamic_grain=true, keep_tv_range=false, output_depth=10) |
|
30th May 2020, 21:45 | #488 | Link | |
Registered User
Join Date: Oct 2001
Posts: 454
|
Quote:
|
|
30th May 2020, 21:50 | #489 | Link | |
Registered User
Join Date: Oct 2001
Posts: 454
|
Quote:
https://github.com/jiangsutx/SPMC_VideoSR https://www.youtube.com/watch?v=0WnwS1EOx3M But these have to be differentiated from the "repainting" models... |
|
31st May 2020, 00:34 | #490 | Link |
Registered User
Join Date: May 2020
Posts: 77
|
Reiner,
What would you call an approach like ESRGAN? According to the description of the model: "how do we recover the finer texture details when we super-resolve at large upscaling factors? ... Our deep residual network is able to recover photo-realistic textures from heavily downsampled images on public benchmarks." They use phrases like "recover" as opposed to "approximate" or "repaint." Are they obfuscating their own approach, or are they one of the models that actually recovers data? |
31st May 2020, 01:17 | #491 | Link | |
Registered User
Join Date: Dec 2002
Location: Region 0
Posts: 1,436
|
Quote:
|
|
31st May 2020, 04:58 | #492 | Link | |
Registered User
Join Date: Mar 2011
Posts: 4,823
|
Well I'll confess after trying some upscaling with Avisynth, I'm now starting to wonder just how clever the clever upscaling is by comparison.
I took the original lossless h264 DVD samples and upscaled them to 4k in Avisynth. I had to do it using 2 processes and hobble x264 a little, otherwise my poor old XP machine would run out of memory, but here's the files in the zip file and how they were created etc. SFE-1 nnedi3 4k rec.709.mkv SFE-2 nnedi3 4k rec.709.mkv Both upscaled using the following script. I forgot the original upscales weren't color converted so the colors are a little different, but that's not what the comparisons were about. There may be better ways to sharpen than with LSFMod, but without a lot of experimenting, it's the only sharpening method I trust not to look horrible. There's only a frame or two of live action in each sample, but it looks pretty obvious that using the method below would require the live secions to either be denoised first, or sharpened far less so the result isn't sharpened noise, however this was primarily to look at how nnedi3 would compare for the CGI. Quote:
SFE-1_4.00x_2560x1920_Gaia-CG.mp4 SFE-2_4.00x_2560x1920_Gaia-CG.mp4 The included screenshots are the same frame from SFE-1 (the nnedi3 screenshots are directly from the Avisynth output (no-re-encoding) so any advantage they have in terms of accuracy has now been declared), and the versions upscaled by JoelHruska are upscaled from my IVTC'd SD encodes of the original source, so that's their disadvantage declared too. The screenshots with 4K in the name are the full upscaled frame. The screenshots not labelled 4k were taken using the PrintScreen button with MPC-HC only displaying 1080p worth of the frame on my 1080p monitor. That way the 1080p screenshots can be compared without the need for resizing on a 1080p monitor. Because I forgot about the color correction thing when encoding, the nnedi3 screenshots include a version that wasn't color converted to rec.709. The samples upscaled by JoelHruska are also included because I was starting to get confused with the multiple sample uploads myself, so the nnedi3 and "Gaia-CG" upscales are both included. The clever upscaling does clean up the line wobbling/aliasing more, but the rest, I'm not so sure it's better. Maybe there's a better anti-aliasing filter than QTGMC that could be used first, before upscaling with Avisynth? nnedi3 comparison.zip (79.8 MB) Last edited by hello_hello; 31st May 2020 at 05:18. |
|
1st June 2020, 01:47 | #494 | Link | |
Registered User
Join Date: May 2020
Location: Canada
Posts: 49
|
Quote:
|
|
1st June 2020, 16:41 | #498 | Link | |
Registered User
Join Date: May 2020
Location: Canada
Posts: 49
|
Quote:
Maybe I misunderstood and it actually can scale by 6x internally? Also, I just found out that Topaz VEAI can be invoked from the command line. If invoked with -? or -h, it will show a list of all available arguments. I haven't tested it yet, but this looks promising for incorporating VEAI into a batch script! |
|
1st June 2020, 22:03 | #499 | Link | |
Registered User
Join Date: Oct 2001
Posts: 454
|
Quote:
CLI can be used for batches, but itīs incomplete at the moment, some stuff missing. Itīs on the roadmap of TOPAZ, hopefully theyīll stick with it and clean this feature up. |
|
1st June 2020, 22:34 | #500 | Link | |
Registered User
Join Date: Oct 2001
Posts: 454
|
Quote:
"recover" is a fuzzy term - ESRGAN actually is one of the "we make stuff up" methods (looks good, but is not original, but pleasing to the viewer (in case of video - more about this later)). There are some, which CAN reveal some detail by looking at multiple frames. Itīs best - in my oppinion - to combine both (VEIA actually does combine both methods to a certain extend - but Iīd love to see a selection on what to turn on or off).. More when I come back.. |
|
Thread Tools | Search this Thread |
Display Modes | |
|
|