Cameras offer a ubiquitous, high-bandwidth source of data about the world around us, providing many opportunities for computational approaches to real-world problems. In this talk, I will show how insights from art, science, and engineering can help us connect progress in visual computing with typically non-visual problems in other domains, allowing us to leverage the convenience and power of video to solve new problems. The first section of the talk will focus on visual vibration analysis: I will show how insights from physics can help us extract sound from silent video, reason about structural and material properties that are perceptually invisible to humans, and even build interactive physical simulations of visible objects. The second section of the talk will give an overview of how similar methodologies can be applied to artistic domains, using insights from music, dance, and cinematography to design computational tools that offer creative control over large amounts of media.