Adaptive Densely Connected Single Image Super-Resolution

Tangxin Xie, Xin Yang, Yu Jia, Chen Zhu, Xiaochuan Li

ICCVW 2019 pp. 3432-3440

doi:10.1109/ICCVW.2019.00426 /iccvw/2019/xie2019iccvw-adaptive/

Abstract

For a better performance in single image super-resolution(SISR), we present an image super-resolution algorithm based on adaptive dense connection (ADCSR). The algorithm is divided into two parts: BODY and SKIP. BODY improves the utilization of convolution features through adaptive dense connections. Also, we develop an adaptive sub-pixel reconstruction layer (AFSL) to reconstruct the features of the BODY output. We pre-trained SKIP to make BODY focus on high-frequency feature learning. The comparison of PSNR, SSIM, and visual effects verify the superiority of our method to the state-of-the-art algorithms.

ICCVW Semantic Scholar

Cite

Text

Xie et al. "Adaptive Densely Connected Single Image Super-Resolution." IEEE/CVF International Conference on Computer Vision Workshops, 2019. doi:10.1109/ICCVW.2019.00426

Markdown

[Xie et al. "Adaptive Densely Connected Single Image Super-Resolution." IEEE/CVF International Conference on Computer Vision Workshops, 2019.](https://mlanthology.org/iccvw/2019/xie2019iccvw-adaptive/) doi:10.1109/ICCVW.2019.00426

BibTeX

@inproceedings{xie2019iccvw-adaptive,
  title     = {{Adaptive Densely Connected Single Image Super-Resolution}},
  author    = {Xie, Tangxin and Yang, Xin and Jia, Yu and Zhu, Chen and Li, Xiaochuan},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2019},
  pages     = {3432-3440},
  doi       = {10.1109/ICCVW.2019.00426},
  url       = {https://mlanthology.org/iccvw/2019/xie2019iccvw-adaptive/}
}