Nicholas P. Lyons

Templated recursive image composition

With the proliferation of image acquisition and consumption, there is an increasing need for solutions that help ordinary people create high quality image composites. In most solutions today, image layouts are provided as fixed templates, which offer the potential of visually diverse layout sets. However, the layout choices are limited to those selected in advance by the template designer; and the library may not support a particular image count, aspect ratio set or spatial distribution. To ameliorate these shortcomings, we propose an image layout framework called Templated Recursive Image Composition. TRIC is template-based in that every layout is based on a template specification. However, TRIC is also generative in that virtually any image set can be accommodated as long as there is at least one image for every region in the template specification. Constraints ensure respect for image aspect ratios; for spacing in the layout interior; and for proportions and placement of sublayouts corresponding to regions in the template specification. We present a description of TRIC, results that demonstrate its versatility, and a user study that supports its acceptability.