LIT: A System and Benchmark for Light Understanding

A modern lighting system should automatically calibrate itself (light commissioning), assess its own status (which lights are on/off and how dimmed), and allow for the creation or preservation of lighting patterns (adjustability), e.g. after the sunset. Such a system does not exist today, nor (real) data, labels, or metrics are available to compare with and foster progress. In this paper we set the baselines to such a computational system, called LIT, and its applications. Using computational imaging we try to model and benchmark the light variations of indoor scenes with different illuminations (including natural light) and luminaire setups. We show that our lighting system can be easily trained with no manual intervention; after that, the benchmark allows to test automatic calibration (LIT-EST), status awareness (LIT-ID) and relighting (RE-LIT) as application.