Axel Mertes has a great idea for: New AI Scaling Method

[tekmeeeout (Tek)]

Continuing the discussion from [Video Enhance AI Feature Requests]

This is his original post below:
(https://community.topazlabs.com/t/video-enhance-ai-feature-requests/20542/157):

Feature Wish: NEW AI Scaling Method

I just recently stumbled over this amazing two minute paper video, that blew my mind:

Enhance! Super Resolution Is Here!

If you think GigaPixel AI and VEAI are outstanding in terms of scaling, that this is squarely nothing compared to what this approach seems to promise:

(Screen grabs from the video linked above from Two Minute Papers youtube channel)

I want to do THIS with my old PAL interlaced videos…
No idea if that ONLY works with faces right now and how much computing resources it might take to make this work for full images, but the direction is clear I guess.

The BIG questions are: Will this work, will it work “in time” and will it work temporary stable for video/film usage?

Regardless of all this, if those results are true then this is mind boggling.

[sokr1114]

i saw the video too on two-minute papers, but I tried it in the google colab and the results were bad, I don’t know I do something wrong or what, but here is the colab to test it:
Google Colab

PS: it will take about 40 Min to enhance one photo

but here is another colab with much better results :

Google Colaboratory

hope you test the two different colab and tell me your feedback.

[lhkjacky (Jacky)]

There are many software can restore face better than GAI / VEAI.
For example, Remini APP, MyHeritage web and Tencent ARC’s GFPGAN.

Gigapixel Face Refinement vs Remini

I found that there are many open-source face upscale AI code in Github. And their result are even better than Remini and MyHeritage. Just curious, why Topaz lab don’t “borrow” some open source Face Reconstruction AI algorithm into Gigapixel. I have tested your image using Face Restoration AI created by Tencent ARC. And here is the result. Clearly the result is much better than GAI’s Face refinement. [5d3b8c0356a975159ff25bd1c4df677132ee027c_cr_00] …

Which AI is the best at Upscale Tiny Face?

Gigapixal AI is a excellent AI upscale software, one of the best on the market. However, GAI is not perfect yet, it have a weakness on enlarging tiny human face. I have a question for all of you, which software you tried have the best ability to upscale tiny face ? Here is a example. Original crop: [Original%20Face%20crop] Upscale by GAI standard mode 6x Auto (Face refinement ON): [5] Upscale by GAI lowres mode 6x Auto (Face refinement ON): [5] Ups…

Here is an example I upscaled with Tencent ARC’s GFPGAN.

I also tested with sample image shown in the Google SR3 video.

Here is the upscaled image by Tencent ARC’s GFPGAN
(It may not look as detail as Google SR3, but it only took a few seconds to process)

---

There are also AI software built in Face restoration for video such as, AVCLabs Video Enhancer AI.

Competitor to VEAI

I found a competitor software to VEAI Video Enhance AI: Enhance the Video Quality with the Power of AI (any-video-converter.com) But on closer inspection, although in the presentation video it looks almost as good, the interface looks very similar to VEAI but with fewer options. For example, the preview option is missing and there is only one output format. there are not as many models depending on the type of video to improve. See the video: https://youtu.be/CWX3ZsA-M74 That be…

Source:

VEAI (ALQ 12 4x):

AVCLabs (Ultra Upscale x4)

[tekmeeeout (Tek)]

That’s very interesting!! Yeah, they should definitely incorporate some of these types AI models capable of restoring like this. It would be cool if it was like an entire scene that it could restore rather than just faces.

[tekmeeeout (Tek)]

I am not sure… I will have to try it out myself sometime when I get around to it. Thanks for sharing your input.