Animating Still Landscape Photographs Through Cloud Motion Creation

Animating landscape photographs can create an engaging viewing experience and has long been an active area of multimedia research. Images can be used to create an illusion of movement, thereby providing more vivid and interesting visuals. Among numerous objects in visual scenes, clouds appear as a common element in landscape photos but are challenging to manipulate because clouds are ill-posed structures without concrete forms and present motion with very high degrees of freedom and arbitrary shape deformation. This paper addresses the generation of dynamic imagery from a still photo through automatic motion creation. First, a cloud appearance model is acquired by representing each pixel in the sky region as a combination of two computable image properties, i.e., Cloudiness estimates cloud density and Cloud Structure gives the corresponding cloud shape and texture. Then, based on the obtained Cloudiness and Cloud Structure, a content-aware wind field is generated to synthesize the motion of cloud flow. Experimental results demonstrate that our approach can work well on various types of cloud images and produce visually convincing dynamic imagery of landscape photos. Furthermore, we showcased several extended multimedia applications to validate that the proposed framework is generic and widely extensible to other vapor-like objects like mist and smoke. Please see http://mclab.citi.sinica.edu.tw/demo/dynamicimagery.htm for demos.