Samsung is committed to delivering best-in-class camera experiences in all conditions. Since the introduction of the Galaxy S10, the Samsung Galaxy series has harnessed artificial intelligence (AI) technologies in its cameras to help users capture every epic moment anytime, anywhere.
As part of this, Samsung developed the Scene Optimizer feature, a camera functionality which uses advanced AI to recognize objects and thus deliver the best results to users. Since the introduction of the Galaxy S21 series, Scene Optimizer has been able to recognize the moon as a specific object during the photo-taking process, and applies the feature’s detail enhancement engine to the shot.
When you’re taking a photo of the moon, your Galaxy device’s1 camera system will harness this deep learning-based AI technology, as well as multi-frame processing in order to further enhance details. Read on to learn more about the multiple steps, processes and technologies that go in to delivering high-quality images of the moon.
| If users wish to take a picture without the support of AI, users can easily deactivate Scene Optimizer by heading to: Camera → Camera Settings → Scene Optimizer → Off |
Understanding Super Resolution and Scene Optimizer
In order to take a clear photo of the moon, Galaxy cameras harness Super Resolution to synthesize more than 10 images taken at 25x zoom or higher. The image taken at 25x zoom or above needs to eliminate noise and enhance clarity and other details.
Super Resolution technology helps produce images through multi-frame composition. When Scene Optimizer is turned on and the moon has been recognized as an object, the camera will deliver users a bright and clear image through the detail enhancement engine of Scene Optimizer on top of the Super Resolution technology.
AI Deep Learning for Moon Object Recognition
The engine for recognizing the moon was built based on a variety of moon shapes and details, from full through to crescent moons, and is based on images taken from our view from the Earth.
It uses an AI deep learning model to detect the presence of the moon and identify the area it occupies – as denoted by the square box – in the relevant image. Once the AI model has completed its learning, it can detect the area occupied by the moon even in images that were not used in training.
&
