Canon has developed a neural network, deep learning-powered image processing technology that can drastically improve the quality of images by reducing noise, correcting colour, and removing lens imperfections such as aberrations and blurring.

The technology uses a massive database of images and Canon’s unique knowledge to sense camera settings and how to correct them. It also includes noise reduction, colour interpolation, and aberration diffraction correction features. Canon has not clarified if this technology will be applied to existing images or built into its cameras.