ML Anthology

Context-Constrained Hallucination for Image Super-Resolution

Jian Sun, Jiejie Zhu, Marshall F. Tappen
CVPR 2010 pp. 231-238
doi:10.1109/CVPR.2010.5540206 /cvpr/2010/sun2010cvpr-context/

Abstract

This paper proposes a context-constrained hallucination approach for image super-resolution. Through building a training set of high-resolution/low-resolution image segment pairs, the high-resolution pixel is hallucinated from its texturally similar segments which are retrieved from the training set by texture similarity. Given the discrete hallucinated examples, a continuous energy function is designed to enforce the fidelity of high-resolution image to low-resolution input and the constraints imposed by the hallucinated examples and the edge smoothness prior. The reconstructed high-resolution image is sharp with minimal artifacts both along the edges and in the textural regions.

PDF CVPR Semantic Scholar

Cite

Text

Sun et al. "Context-Constrained Hallucination for Image Super-Resolution." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010. doi:10.1109/CVPR.2010.5540206

Markdown

[Sun et al. "Context-Constrained Hallucination for Image Super-Resolution." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010.](https://mlanthology.org/cvpr/2010/sun2010cvpr-context/) doi:10.1109/CVPR.2010.5540206

BibTeX

@inproceedings{sun2010cvpr-context,
  title     = {{Context-Constrained Hallucination for Image Super-Resolution}},
  author    = {Sun, Jian and Zhu, Jiejie and Tappen, Marshall F.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2010},
  pages     = {231-238},
  doi       = {10.1109/CVPR.2010.5540206},
  url       = {https://mlanthology.org/cvpr/2010/sun2010cvpr-context/}
}