Highly realistic video communication, which provide feel of existence of remote users and objects, is expected to be a next generation communication using the internet. To achieve such system, it is important to reproduce not only high quality image but also sense of directivity depending on user's position. However, viewpoint image synthesis is usually not easy for live action. In this paper an approach for viewpoint image synthesis method using multi-camera images and approximate depth information, which can provide smooth motion parallax with high speed processing and high image quality, will be demonstrated.
View full abstract