In the new beta version of iOS 13, Deep Fusion photo processing feature has appeared for developers.
This mode is primarily designed for insufficient light conditions - on the street in the evening or in a room with poor light. Deep Fusion is automatically turned on and works unnoticed by the user, and the photo is not even marked.
The technology uses machine learning to process images, optimize textures, reduce noise and improve overall image quality. The essence of the technology is that even before you press the shutter button, the camera will already take four pictures. After that, four more photos will be made. Then the best moments from all the images will be combined into one photo of the highest possible quality in HDR.
Deep Fusion doesn’t ask permission to be enabled, so you won’t know the moment it began functioning. The photo is not marked in any way in the gallery and is not displayed in the file data.