Content-aware Photo Collage Using Circle Packing

With the prevalence of smartphones equipped with high resolution cameras and the emergence of widely popular photo management and sharing websites, people have access to digital photo collections more often than before. Photo collage, as an impor-tant means for summarizing and exhibiting a collection of photos, has received consid-erable attention recently. It aims to create a compact, informative, and visually pleasant single image representation by sticking together the pictures from a photo collection.Since manually creating such a collage is time-consuming and generally requires professional image editing skills, automatic solutions have been intensively studied in the research community. In this thesis, we present a novel approach for automatically creating the photo collage that assembles the interest regions of a given group of images naturally.Previous methods on photo collage are generally built upon a well-defined opti-mization framework which computes all the geometric parameters and layer indexes for input photos on the given canvas by optimizing a unified objective function that quantifies the criteria for a visually pleasing collage. Due to the complex non-linear form of optimization framework, optimal parameters for different photos are tightly coupled, making the update of a photo’s state affect other photos globally or locally. This limits their scalability and efficiency.From the geometric point of view, we recast the generation of collage as a region partition problem such that each image is displayed in its corresponding region par-titioned from the canvas. The core of this is an efficient power diagram based circle packing algorithm, which arranges a series of circles assigned to input photos com-pactly in the given canvas. To favor important photos, the circles are associated with image importances determined by an image ranking process. A heuristic search pro-cess is developed to ensure that salient information of each photo is displayed in the polygonal area resulting from circle packing.With our new formulation, each factor influencing the state of a photo is optimized in an independent stage, and computation of the optimal states for neighboring photos are completely decoupled. This improves the scalability of collage results and ensures their diversity. We also devise a saliency-based image fusion scheme to generate seam-less compositive collage.Our approach can generate the collages on non-rectangular canvases and supports interactive collage that allows the user to refine collage results according to his/her personal preferences. We conduct extensive experiments and show the superiority of our algorithm by comparing against previous methods.