"Canon's in-camera AI is going to change everything," says James Artaius

Canon's EOS R5 Mark II can upscale images by 400% and can remove 2-stops of ISO noise - all in-camera! How good is it? It's THIS good...

- 

Canon has potentially made the megapixel race redundant. Gone will be the days of sensors chasing ever-higher pixel counts, and cameras may never be the same again. What am I talking about? Let me explain.

The Canon EOS R5 Mark II (and EOS R1) is packed with incredible new in-camera neural network processing tech, powered by AI and deep learning. The two biggest party tricks are 400% In-Camera Upscaling and 2-stop Noise Reduction. In-Camera Upscaling takes 45MP images taken on the R5 Mark II, and transforms them into 180MP super-sized images.

It's absolutely brilliant! Unlike post-production software such as Topaz, which has to use guesswork and AI to interpolate and completely invent the pixels and data when it upscales your images, Canon's technology doesn't have to guess anything: it knows everything about your image using the information recorded to the camera at the moment of capture.

It knows what lens you used, the aberrations created by its optical formula, the ISO sensitivity and the noise it introduces, the aperture and its effect on defocus, the white balance, the bit depth... Canon's tech simply embellishes all the information it already has about your photo.

How do you upscale an image?

Upscaling an image is simple.