Ted Sim, Aputure
From the dawn of cinema, lighting has played a crucial role in guiding audiences on where to look and how to feel. They can place focus on a specific character, prop, or part of a scene, help build and compose mise-en-scène, and convey the internal psychology of characters and the emotional tone of a narrative.
However, lighting is a challenging task. It balances out a host of technical and creative skills that take years to master while engaging multiple people, such as film directors, directors of photography, gaffers, and actors. It requires experience with numerous techniques, expensive and cumbersome equipment, and setups that are difficult to learn, teach and communicate with precision.
In this research, we are investigating how deep learning and new hardware technologies can be combined to make film lighting easier to learn, create, and communicate. By creating predictive and on-set lighting assistants, we are making film lighting more accessible, flattening pre- and post-production processes, and using artificial intelligence to put humans at the center of the creative process.
Synthetic lighting data for model training