Indoor Lighting Estimation using an Event Camera

Zehao Chen, Qian Zheng, Peisong Niu, Huajin Tang, Gang Pan

Abstract: Image-based methods for indoor lighting estimation suf- fer from the problem of intensity-distance ambiguity. This paper introduces a novel setup to help alleviate the ambi- guity based on the event camera. We further demonstrate that estimating the distance of a light source becomes a well-posed problem under this setup, based on which an optimization-based method and a learning-based method are proposed. Our experimental results validate that our approaches not only achieve superior performance for in- door lighting estimation (especially for the close light) but also significantly alleviate the intensity-distance ambiguity.