Exposure enhancements based on human segmentation

Abstract

A method involves obtaining a first image depicting a subject. The method further involves determining a subject segmentation mask representing areas of the subject as depicted in the first image, based on the first image. The method further involves determining one or more exposure gain parameters for the first image based on the subject segmentation mask. The method also involves obtaining a second image depicting the subject. The method further involves applying one or more exposure gain parameters from the first image to the second image, based on the determination that the second image omits a certain area of ​​the subject, and including the certain area in the first image.

Images