Beauty Moment Rendering via Face Happiness Scoring

Abstract

Nowadays, with the rapid development of technology and an energetic lifestyle, people tend to use electronic devices to capture moments. Thus, the need to have a delightful selfie is increasing. This work introduces a Beauty Moment Rendering via Face Happiness Scoring framework, which aims to generate a key-frame that summarizes a short selfie video. Given a set of consecutive photos as input, our approach selects a single image and renders a face for each person at their happiest moment. In order to select a suitable key-frame, we decide to combine the eyes and emotion information as our aggregated score. First, the method detects and tracks the faces in the video frames. Then, the face that has the highest score of each person will be rendered on the result key-frame with the eye gazes being redirected based on a generative model. To the best of our knowledge, we are among the first to address the problem, which comprises video summarization and face beautification.