Automatic cinematography for 360 video
This addresses the challenge of automating video editing for immersive 360-degree content, which is incremental as it builds on existing cinematography techniques.
The paper tackles the problem of generating visually interesting camera paths from 360 videos, resulting in an automatic cinematography method that constructs and renders the best shot hypotheses based on scene object information.
We describe our method for automatic generation of a visually interesting camera path (automatic cinematography)from a 360 video. Based on the information from the scene objects, multiple shot hypotheses for different shot types are constructed and the best one is rendered.