Comment by tonymillion

3 years ago

Simple solution: keep the raw image and AI it on the fly (this is a hypothetical future remember)

Bonus feature: new display devices get better trained / new AI features for free

So now not only are there AI-imagined details in your images but those details are also different depending on which device the image is viewed on. Lovely.

  • Or no AI enhancements, since you have the raw photo sensor data, even better you can pick your own AI algorithms to apply to the image.

    E.g. from the raw data we know the sensor, we can train a specific AI to enhance the image from the known physical properties of the CCD