Batteries, camera, action! Learning a semantic control space for expressive robot cinematography

TL;DR

This paper introduces a data-driven framework that maps semantic descriptors like 'calm' or 'establishing' to camera control parameters for autonomous aerial cinematography, making expressive shot generation accessible to non-technical users.

Contribution

It develops a semantic control space for camera parameters, based on human perception and cinematography principles, enabling intuitive editing of complex camera behaviors.

Findings

Model successfully generates shots with expected expressive qualities.

System generalizes across different scenes in simulation and real-world.

Participants rated generated shots as matching desired semantic descriptors.

Abstract

Aerial vehicles are revolutionizing the way film-makers can capture shots of actors by composing novel aerial and dynamic viewpoints. However, despite great advancements in autonomous flight technology, generating expressive camera behaviors is still a challenge and requires non-technical users to edit a large number of unintuitive control parameters. In this work, we develop a data-driven framework that enables editing of these complex camera positioning parameters in a semantic space (e.g. calm, enjoyable, establishing). First, we generate a database of video clips with a diverse range of shots in a photo-realistic simulator, and use hundreds of participants in a crowd-sourcing framework to obtain scores for a set of semantic descriptors for each clip. Next, we analyze correlations between descriptors and build a semantic control space based on cinematography guidelines and human perception studies. Finally, we learn a generative model that can map a set of desired semantic video descriptors into low-level camera trajectory parameters. We evaluate our system by demonstrating that our model successfully generates shots that are rated by participants as having the expected degrees of expression for each descriptor. We also show that our models generalize to different scenes in both simulation and real-world experiments. Data and video found at: https://sites.google.com/view/robotcam.