Upscaling with better detail using Proteus in TVAI v3.x

So i take it that, in my case where it’s usually digitized files @480, to do the necessary deinterlace, noise reduction first, and then when uoscaling apply sharpen?

Everything I’ve mentioned recently assumes we are already working with deinterlaced input. However, sharpening at original size can be problematic. Being that you’re working at the same pixel width and height, attempting to sharpen at original is sure to flatten something. The best solution is getting the adjusting for better (more) detail preferentially over denoising. So crank up detail enough so you get a clearer image, detail-wise, and the push up the denoise just enough to avoid eroding detail.

Next, you need to check to see that detail isn’t so high that it overdoes it and begins to ‘fake’ recognition. If so, crank denoise and detail down a little to see if you can get the optimum result.

In regard to deinterlacing: Deinterlacing is an important subject all by itself. Some of the most basic problems there are the various interlacing methods used, including the hacks for making the media compatible with the playback hardware in use at the time. - There is no single be-all and end-all solution for deinterlacing video. But one of the biggest problems is that the video was actually interlaced before it was compressed into am MPEG video format. That means that any good deinterlacing methodology should also be able to do decompression and noise reduction before the actual deinterlacing process should be started. - Unfortunately, you will not find many of these. The end result is that a lot of noise gets ‘baked’ into the deinterlaced video. - Interpolation can help remediate this problem somewhat, but that is also problematic.

This subject should get better treatment in another thread. - There already is one, but I think it may be getting out of date in term of TVAI’s capabilities in the deinterlace area.

1 Like

pd white, do you mean pushing up denoise above relative? To be honest, i have a hard time to beat Auto… Does that relative -100 mean bypass that function or even invert it? Cheers!
will try some more two steps.

In Relative mode, by default everything is set to ‘auto.’ You will see this as “0” on each control’s line. Reducing or increasing the value biases the auto behavior. For example: Increasing denoise by five make the denoise part of the Proteus algorithm work harder.

If memory serves the extra setting is a ‘bias’; changing it just elevates (or lowers) the response curve for that auto setting.

And, setting a control to -100, may not turn it off. But you can try it and see.

I know that the deblur setting is best at the middle unless you like jumpy frames or anti-alising.

The main problem is turning too many settings too high. Doing so can push the other settings off balance. - So easy does it. Never push, unless you like surprises… :nerd_face:

4 Likes

Thank you. Great info.

I cannot get relative to auto to pick a value for Anti-alias/Deblur that doesn’t create fake details, so I’ve been using manual.
You are totally right about going easy on any value change and some values countering other values!

I don’t have the patience right now to try multiple passes. For now, using the methods you have explained in this topic, I have at least got a very grainy old video to be upscaled and not be grainy. It’s still just as blurry with a little loss of detail, but I’m pleased with it. The far off faces don’t look creepy and it doesn’t look like a painting. Most importantly, it looks better than a simple Lanzcos filter upscale.

1 Like

Good. to hear you’re having some success.

FYI: There are some on-line tutorials that explain the controls. - While they do describe specifically what the function is for each control, they don’t go very deeply into an explanation of how it is used, and rarely it’s relationship to the other settings.

I suppose their expectation is that you’re going to use your own technique for using them or you already know what they know. - The latter problem is not uncommon in technical documentation; which usually renders most of the information useless.

:thinking: :nerd_face:

1 Like