ML Anthology

Picture Collage

Jingdong Wang, Long Quan, Jian Sun, Xiaoou Tang, Heung-Yeung Shum
CVPR 2006 pp. 347-354
doi:10.1109/CVPR.2006.224 /cvpr/2006/wang2006cvpr-picture/

Abstract

In this paper, we address a novel problem of automatically creating a picture collage from a group of images. Picture collage is a kind of visual image summary - to arrange all input images on a given canvas, allowing over-lay, to maximize visible visual information. We formulate the picture collage creation problem in a Bayesian frame-work. The salient regions of each image are firstly extracted and represented as a set of weighted rectangles. Then, the image arrangement is formulated as a Maximum a Posterior (MAP) problem such that the output picture collage shows as many visible salient regions (without being overlaid by others) from all images as possible. Moreover, a very efficient Markov chain Monte Carlo (MCMC) method is designed for the optimization. Applications to desktop image browsing and image search result summarization demonstrate the effectiveness of our approach.

CVPR Semantic Scholar

Cite

Text

Wang et al. "Picture Collage." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006. doi:10.1109/CVPR.2006.224

Markdown

[Wang et al. "Picture Collage." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006.](https://mlanthology.org/cvpr/2006/wang2006cvpr-picture/) doi:10.1109/CVPR.2006.224

BibTeX

@inproceedings{wang2006cvpr-picture,
  title     = {{Picture Collage}},
  author    = {Wang, Jingdong and Quan, Long and Sun, Jian and Tang, Xiaoou and Shum, Heung-Yeung},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2006},
  pages     = {347-354},
  doi       = {10.1109/CVPR.2006.224},
  url       = {https://mlanthology.org/cvpr/2006/wang2006cvpr-picture/}
}