Two patents filed by Nintendo have recently been published, showing the company’s potential plans for AI upscaling technology.
The patents, which were originally filed in March 2020 but were published on Thursday, detail “systems and methods for machine learned image conversion”.
It describes the process of taking a source image, dividing it into blocks of pixels and giving each block some context data. These are all then added to an ‘activation matrix’, which is run through a trained neural network to convert the image to a higher resolution.
Although it’s not specifically clear what purpose Nintendo has for this patent – which, at the time of writing, has yet to be approved – it does list some examples of how the process can be implemented.
Switch OLED official unboxing
One example given details a process similar to the Switch’s main functionality, where a game can run at one resolution while a device is being powered by a battery, but when plugged into a power socket or connected to a TV the output can be upscaled to 1080p.
Another example discusses the process’s potential use in cloud gaming, in which cloud-based systems can send a compressed, low-res image to the player’s device, which will then use AI to upscale it to 1080p at the user’s end to reduce latency.
Nintendo includes a diagram with the patent which shows a 540p image being upscaled to a 1080p one. It does, however, mention that other upscaling processes, including upscaling to 4K, would be possible.
It states: “It will be appreciated that while the example shown […] relates to transforming a 540p image to a 1080p image, the techniques herein may be applied to other image sizes (e.g. 720p to 1080p, 480p to 1080p, 1080p to 1440p, 1080p to 4K, 720p to 4k, etc).”
It was reported and expected earlier this year that Nintendo was shaping up to announce a new ‘Switch Pro’ model that included 4K resolution support.
Instead, the company announced the Nintendo Switch OLED model in July, which includes a larger 7-inch OLED screen, but no 4K capabilities.