To make a great portrait, your phone first has to see a face in the picture. So, we trained our face detector models to “see” more diverse faces in more lighting conditions.

Auto-white balance models help determine color in a picture. Our partners helped us hone these models to better reflect a variety of skin tones.

Similarly, we made changes to our auto-exposure tuning to balance brightness and ensure your skin looks like you – not unnaturally brighter or darker.

Stray light shining in an image can make darker skin tones look washed out, so we developed an algorithm to reduce its negative effects in your pictures.

Getting a sharp portrait in dim light shouldn’t depend on how you look, so we significantly cut down image blur for people with darker skin tones in Night Sight portraits.

Our experts also helped us improve Google Photos’ auto enhance software — so you can achieve a beautiful, representative photo regardless of when you took the photo, or which device you used.