Abstract
Group photos have become indispensable in various gathering scenarios, such as family reunions, friends' gatherings, competitions, conferences, store openings, and school graduation ceremonies. The researchers tried automatically adding people who could not participate in the group photo. However, the current research on generating the pose or position of the person by context prediction of the group photo ignores the individual attributes (such as height and body shape) of the target person and does not consider the pose and boundary of the person at the same time. To address these issues, we propose a virtual group photography model that combines the global context of a group photo and the individual attributes of the target person. The model is divided into two stages. The first stage is to predict the person's position, pose, and boundary in the new group photo based on the context of the input group photo and the person's characteristics. The second stage generates new group photos based on the first stage's pose and boundary results. The experimental results show that our method can significantly improve the harmony and authenticity of the synthesis of people in group photos and synthesize the characters that should exist in the group photo, which is very suitable for the field of group photos.