Epitomic Image Super-Resolution

Yingzhen Yang, Zhangyang Wang, Zhaowen Wang, Shiyu Chang, Ding Liu, Honghui Shi, Thomas S. Huang

AAAI 2016 pp. 4278-4279

doi:10.1609/AAAI.V30I1.9920 /aaai/2016/yang2016aaai-epitomic/

Abstract

We propose Epitomic Image Super-Resolution (ESR) to enhance the current internal SR methods that exploit the self-similarities in the input. Instead of local nearest neighbor patch matching used in most existing internal SR methods, ESR employs epitomic patch matching that features robustness to noise, and both local and non-local patch matching. Extensive objective and subjective evaluation demonstrate the effectiveness and advantage of ESR on various images.

PDF AAAI Semantic Scholar

Cite

Text

Yang et al. "Epitomic Image Super-Resolution." AAAI Conference on Artificial Intelligence, 2016. doi:10.1609/AAAI.V30I1.9920

Markdown

[Yang et al. "Epitomic Image Super-Resolution." AAAI Conference on Artificial Intelligence, 2016.](https://mlanthology.org/aaai/2016/yang2016aaai-epitomic/) doi:10.1609/AAAI.V30I1.9920

BibTeX

@inproceedings{yang2016aaai-epitomic,
  title     = {{Epitomic Image Super-Resolution}},
  author    = {Yang, Yingzhen and Wang, Zhangyang and Wang, Zhaowen and Chang, Shiyu and Liu, Ding and Shi, Honghui and Huang, Thomas S.},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2016},
  pages     = {4278-4279},
  doi       = {10.1609/AAAI.V30I1.9920},
  url       = {https://mlanthology.org/aaai/2016/yang2016aaai-epitomic/}
}