Image Hallucination with Primal Sketch Priors

Jian Sun, Nanning Zheng, Hai Tao, Heung-Yeung Shum

CVPR 2003 pp. 729-736

doi:10.1109/CVPR.2003.1211539 /cvpr/2003/sun2003cvpr-image/

Abstract

We propose a Bayesian approach to image hallucination. Given a generic low resolution image, we hallucinate a high resolution image using a set of training images. Our work is inspired by recent progress on natural image statistics that the priors of image primitives can be well represented by examples. Specifically, primal sketch priors (e.g., edges, ridges and corners) are constructed and used to enhance the quality of the hallucinated high resolution image. Moreover, a contour smoothness constraint enforces consistency of primitives in the hallucinated image by a Markov-chain based inference algorithm. A reconstruction constraint is also applied to further improve the quality of the hallucinated image. Experiments demonstrate that our approach can hallucinate high quality super-resolution images.

CVPR Semantic Scholar

Cite

Text

Sun et al. "Image Hallucination with Primal Sketch Priors." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003. doi:10.1109/CVPR.2003.1211539

Markdown

[Sun et al. "Image Hallucination with Primal Sketch Priors." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003.](https://mlanthology.org/cvpr/2003/sun2003cvpr-image/) doi:10.1109/CVPR.2003.1211539

BibTeX

@inproceedings{sun2003cvpr-image,
  title     = {{Image Hallucination with Primal Sketch Priors}},
  author    = {Sun, Jian and Zheng, Nanning and Tao, Hai and Shum, Heung-Yeung},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2003},
  pages     = {729-736},
  doi       = {10.1109/CVPR.2003.1211539},
  url       = {https://mlanthology.org/cvpr/2003/sun2003cvpr-image/}
}