What is AI upscaling? This handy development in TV picture processing can take the content of a lower resolution than your TV’s own panel. You can also optimize it to get better, sharper, and more detailed.
It may sound almost like regular old upscaling, and you’d be right. The ‘AI’ part just means the upscaling happens with a greater awareness of context.
Read more on this article to learn more about AI Upscaling and how it works.
That’s because Al upscaling involves creating new pixels of image information to add detail where there wasn’t any before. Filling the gaps to recreate a higher-resolution image, all the while using machine learning to enhance the result.
But top TV brands also as Nvidia, maker of PC graphics hardware now have compelling 4K and 8K AI upscaling techniques. And this elevates ‘AI Upscaling’ beyond the meaningless marketing buzzword it might have been.
What Is AI Upscaling?
AI Upscaling attempts to form sub-4K footage look more like video shot at your display’s native resolution. How is AI upscaling different from normal upscaling? AI upscaling is just smarter upscaling.
Both types prep video for displays with a better pixel count. But ‘AI upscaling’ uses machine learning to enhance the image.
Who offers the simplest AI upscaling? Sony and Samsung are at the highest of the AI upscale league in the world of TVs.
Nvidia’s Shield TV box also has very effective upscaling, should you have a 4K TV with a basic scaler but otherwise satisfying image quality.
Which TVs have AI Upscaling?
All top-end TVs have a kind of AI upscaling, even though the manufacturer doesn’t explicitly use the term ‘AI’.
Samsung’s AI upscaling is offered in sets with its Quantum Processor hardware. These include the Samsung Q70, Q75, Q80, Q90, and Q900 series.
This means the new QN900A and QN95A are both included. Sony’s top upscaling is termed X-Reality Pro or XR Upscaling based on the set you purchase. 4K and 8K XR Upscaling are Sony’s best.
LG uses the term ‘AI Upscaling’ too, except for the best results you’ll need a TV with an α9 Gen4 or α7 Gen 4 CPU. These include its top OLED TVs and also the higher-end LG Nano cell screens.
How Does AI Upscaling Work?
Take a bit of 1080p content. It’s designed for displays with a bit over two million pixels. But 4K TVs have almost 8.3 million pixels, while 8K TVs pack in a staggering 33 million pixels.
The simplest method to fill in those additional pixels is doubling, where blocks of pixels repeat similar visual information.
This results in block images that are better for retro games than they’re for home movies. It can be called ‘nearest neighbor resizing’.
Another approach is creating interstitial pixels, smoothing out transitions between pixels in low-res sources. A bright pixel next to a dark pixel within the source video would therefore be bordered by mid-level brightness pixels within the final upscaled image. This leads to a soft image.
The most pleasing explanation of AI upscaling to the human brain is that these TV processors can recognize objects like grass, fur, or eyelashes and fill in the detail missing within the source image. But it might be more accurate to say upscaling is powered by algorithms that will recognize contrast patterns common in real-world scenes.
An upscaled engine takes cues from the source material to estimate what the footage would appear as if it were shot in native 4K or 8K.