Image Super-Resolution via Deep Recursive Residual Network

Recently, Convolutional Neural Network (CNN) based models have achieved great success in Single Image SuperResolution (SISR). Owing to the strength of deep networks, these CNN models learn an effective nonlinear mapping from the low-resolution input image to the high-resolution target image, at the cost of requiring enormous parameters. This paper proposes a very deep CNN model (up to 52 convolutional layers) named Deep Recursive Residual Network (DRRN) that strives for deep yet concise networks. Specifically, residual learning is adopted, both in global and local manners, to mitigate the difficulty of training very deep networks; recursive learning is used to control the model parameters while increasing the depth. Extensive benchmark evaluation shows that DRRN significantly outperforms state of the art in SISR, while utilizing far fewer parameters.

Results

Scale factor x2

Scale factor x3

Scale factor x4

Deep Recursive Residual Network Code

Publications

• FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors
  Yu Chen*, Ying Tai*, Xiaoming Liu, Chunhua Shen, Jian Yang
  In Proceeding of IEEE Computer Vision and Pattern Recognition (CVPR 2018), Salt Lake City, UT, Jun. 2018 (Spotlight)
  Bibtex | PDF | arXiv | Code
@inproceedings{ fsrnet-end-to-end-learning-face-super-resolution-with-facial-priors,
  author = { Yu Chen* and Ying Tai* and Xiaoming Liu and Chunhua Shen and Jian Yang },
  title = { FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors },
  booktitle = { In Proceeding of IEEE Computer Vision and Pattern Recognition },
  address = { Salt Lake City, UT },
  month = { June },
  year = { 2018 },
}
• MemNet: A Persistent Memory Network for Image Restoration
  Ying Tai, Jian Yang, Xiaoming Liu, Chunyan Xu
  In Proceeding of International Conference on Computer Vision (ICCV 2017), Venice, Italy, Oct. 2017
  Bibtex | PDF | Code
@inproceedings{ memnet-a-persistent-memory-network-for-image-restoration,
  author = { Ying Tai and Jian Yang and Xiaoming Liu and Chunyan Xu },
  title = { MemNet: A Persistent Memory Network for Image Restoration },
  booktitle = { In Proceeding of International Conference on Computer Vision },
  address = { Venice, Italy },
  month = { October },
  year = { 2017 },
}
• Image Super-Resolution via Deep Recursive Residual Network
  Ying Tai, Jian Yang, Xiaoming Liu
  In Proceeding of IEEE Computer Vision and Pattern Recognition (CVPR 2017), Honolulu, HI, Jul. 2017
  Bibtex | PDF | Code
@inproceedings{ image-super-resolution-via-deep-recursive-residual-network,
  author = { Ying Tai and Jian Yang and Xiaoming Liu },
  title = { Image Super-Resolution via Deep Recursive Residual Network },
  booktitle = { In Proceeding of IEEE Computer Vision and Pattern Recognition },
  address = { Honolulu, HI },
  month = { July },
  year = { 2017 },
}