Paper: Selecting good still frames from a video

In this paper, we train a computer to select still frames from video that work well as candid portraits. Because of the subjective nature of this task, we conduct a human subjects study to collect ratings of video frames across multiple videos. Then, we compute a number of features and train a model to predict the average rating of a video frame.

Pretty neat results!

Download the paper →
Candid Portrait Selection From Video →

Leave a comment

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.