Light Clustering for Dynamic Image Based Lighting

Abstract

High Dynamic Range (HDR) imagery has made it possible to relight virtual objects accurately with the captured lighting. This technique, called Image Based Lighting (IBL), is a commonly used to render scenes using real-world illumination. IBL has mostly been limited to static scenes due to limitations of HDR capture. However, recently there has been progress on developing devices which can capture HDR video sequences. These can be also be used to light virtual environments dynamically. If existing IBL algorithms are applied to this dynamic problem, temporal artifacts viewed as flickering can often arise due to samples being selected from different parts of the environment in consecutive frames. In this paper we present a method for efficiently rendering virtual scenarios with such captured sequences based on spatial and temporal clustering. Our proposed Dynamic IBL (DIBL) method improves temporal quality by suppressing flickering, and we demonstrate the application to fast previews of scenes lit by video environment maps.