Efficient Optimization of Photo Collage
نویسندگان
چکیده
Photo collage is an effective representation for photo summarization and visualization. However, its practical usage is limited by its high computational cost. In this paper, we present efficient optimization techniques based on a novel formulation on markov random fields and several insights unexploited by previous approaches. Our method achieves up to hundreds-fold performance improvement, and user/application specific constraints can be easily integrated. We present new applications including interactive collage refinement and dynamic collage for photo browsing. Preliminary evaluation and user study indicates that our approach extends the usability of photo collage.
منابع مشابه
Photo Browsing with Collage Trees sketches 0174
Technological advances in digital photography have made it possible to acquire and store more pictures than ever before. Unfortunately this has led to massively sized photo collections that becomes difficult to browse. We propose a novel interface to facilitate browsing these large collections. Our approach hierarchically groups the photos, summarizes the groups as a tree of collages, and allow...
متن کاملPhoto Browsing with Collage Trees
Recent advances in technology have made it possible for the average person to acquire thousands of high resolution digital photographs per year. While there are clear advantages to having the ability to amass such large collections it creates new problems when trying to organize, browse and generally interact with the photos. In this paper we introduce the concept of a Photo Collage Tree, a str...
متن کاملSmart Photo Sticking
Smart photo sticking is a novel strategy to automatically arrange a collection of photos in a pleasant collage. The proposed approach improves previous solutions both considering a self-adaptive image cropping algorithm, exploiting visual and semantic information, and introducing an optimization process based on a genetic algorithm. Preliminary results confirm the effectiveness of the proposed ...
متن کاملPicture Collage with Genetic Algorithm and Stereo vision
In this paper, a salient region extraction method for creating picture collage based on stereo vision is proposed. Picture collage is a kind of visual image summary to arrange all input images on a given canvas, allowing overlay, to maximize visible visual information. The salient regions of each image are firstly extracted and represented as a depth map. The output picture collage shows as man...
متن کاملA.: Autocollage
The paper defines an automatic procedure for constructing a visually appealing collage from a collection of input images. The aim is that the resulting collage should be representative of the collection, summarising its main themes. It is also assembled largely seamlessly, using graph-cut, Poisson blending of alpha-masks, to hide the joins between input images. This paper makes several new cont...
متن کامل