A multi-timescale image space model for dynamic cloud illumination

Sky illumination is a core source of lighting in rendering, and a substantial amount of work has been developed to simulate lighting from clear skies. However, in reality, clouds substantially alter the appearance of the sky and subsequently change the scene illumination. While there have been recent advances in developing sky models which include clouds, these all neglect cloud movement which is a crucial component of cloudy sky appearance. In any sort of video or interactive environment, it can be expected that clouds will move, sometimes quite substantially in a short period of time. Our work proposes a solution to this which enables whole-sky dynamic cloud synthesis for the first time. We achieve this by proposing a multi-timescale sky appearance model which learns to predict the sky illumination over various timescales, and can be used to add dynamism to previous static, cloudy sky lighting approaches. • A framework for dynamic cloud lighting synthesis from a single static sky image • Input images from hemispherical sky capture or from recent static generative methods • An learned optical flow based method for hemispherical image cloud movement. • A multi-timescale method for smooth, coherent cloud movement across the sky • Results show smooth cloud movement synthesis applied in various rendering scenarios