방송공학회논문지 (Journal of Broadcast Engineering)

  • 제25권2호
  • /
  • Pages.242-251
  • /
  • 2020
  • /
  • 1226-7953(pISSN)
  • /
  • 2287-9137(eISSN)
한국방송∙미디어공학회 (The Korean Institute of Broadcast and Media Engineers)
권호 표지
DOI QR코드

DOI QR Code

CARDB를 이용한 반복적인 업-다운 샘플링 네트워크 기반의 단일 영상 초해상도 복원

Single Image Super-Resolution Using CARDB Based on Iterative Up-Down Sampling Architecture

  • 김인구 (한양대학교 전자컴퓨터통신공학과) ;
  • 유송현 (한양대학교 전자컴퓨터통신공학과) ;
  • 정제창 (한양대학교 전자컴퓨터통신공학과)
  • Kim, Ingu (Department of Electronics and Computer Engineering, Hanyang University) ;
  • Yu, Songhyun (Department of Electronics and Computer Engineering, Hanyang University) ;
  • Jeong, Jechang (Department of Electronics and Computer Engineering, Hanyang University)
  • 투고 : 2019.12.20
  • 심사 : 2020.02.24
  • 발행 : 2020.03.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

최근 단일 영상 초해상도에 깊은 합성 곱 신경망을 적용한 알고리듬이 많이 연구되었다. 현존하는 딥러닝 기반 초해상도 기법들은 네트워크의 후반부에 해상도를 업샘플링 하는 구조를 가진다. 이러한 구조는 저해상도에서 고해상도로 한 번에 매핑을 하기에 많은 정보를 예측하는 높은 확대율에서 비효율적인 구조를 가진다. 본 논문에서는 반복적인 업-다운 샘플링 구조를 기반으로 하여 채널 집중 잔여 밀집 블록을 이용한 단일 영상 초해상도 기법을 제안한다. 제안한 알고리듬은 저해상도와 고해상도의 매핑 관계를 효율적으로 예측하여 높은 확대율에서 기존의 알고리듬에 비해 최대 0.14dB 성능 향상과 개선된 주관적 화질을 보여준다.

Recently, many deep convolutional neural networks for image super-resolution have been studied. Existing deep learning-based super-resolution algorithms are architecture that up-samples the resolution at the end of the network. The post-upsampling architecture has an inefficient structure at large scaling factor result of predicting a lot of information for mapping from low-resolution to high-resolution at once. In this paper, we propose a single image super-resolution using Channel Attention Residual Dense Block based on an iterative up-down sampling architecture. The proposed algorithm efficiently predicts the mapping relationship between low-resolution and high-resolution, and shows up to 0.14dB performance improvement and enhanced subjective image quality compared to the existing algorithm at large scaling factor result.

키워드

참고문헌

  1. W. T. Freeman, T. R. Jones, and E. C. Pasztor, "Example-based super resolution," In Computer Graphics and Applications, pp. 56-65, 2002.
  2. D. Glasner, S. Bagon, and M. Irani, "Super-resolution from a single image," In International Conference on Computer Vision, pp. 349-356, 2009.
  3. C. Dong, C. C. Loy, K. He, and X. Tang. "Image Super-Resolution Using Deep Convolutional Networks," In Transactions on Pattern Analysis and Machine Intelligence, pp. 295-307, 2016.
  4. B. Lim, S. Son, H. Kim, S. Nah and K. M. Lee. "Enhanced Deep Residual Networks for Single Image Super-Resolution," In Conference Workshop on Computer Vision and Pattern Recognition, pp. 1132-1140, 2017.
  5. M. Haris, G. Shakhnarovich, and N. Ukita, "Deep Back-Projection Networks for Super-Resolution," In Conference on Computer Vision and Pattern Recognition, pp. 1664-1673, 2018.
  6. J. Kim, J. K. Lee and K. M. Lee. "Accurate Image Super-Resolution Using Very Deep Convolutional Networks," In Conference on Computer Vision and Pattern Recognition, pp. 1646-1654, 2016.
  7. Y. Zhang, Y. Tian, Y. Kong, B. Zhong, and Y. Fu, "Residual Dense Network for Image Super-Resolution," In Conference on Computer Vision and Pattern Recognition, pp. 2472-2481, 2018.
  8. K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," In Conference on Computer Vision and Pattern Recognition, pp. 770-778, 2016.
  9. G. Huang, Z. Liu, L. v. d. Maaten, and K. Q. Weinberger, "Densely Connected Convolutional Networks," In Conference on Computer Vision and Pattern Recognition, pp. 2261-2269, 2017.
  10. Y. Zhang, K. Li, K. Li, L. Wang, B. Zhong, and Y. Fu, "Image Super-Resolution Using Very Deep Residual Channel Attention Networks," In European Conference on Computer Vision, pp. 286-301, 2018.
  11. C. Dong, C. C. Loy, and X. Tang. "Accelerating the Super-Resolution Convolutional Neural Network," In European Conference on Computer Vision, pp. 391-407, 2016.
  12. Y. Tai, J. Yang, and X. Liu. "Image Super-Resolution via Deep Recursive Residual Network," In Conference on Computer Vision and Pattern Recognition, pp. 3147-3155, 2017.
  13. J. Kim, J. K. Lee, and K. M. Lee. "Deeply-Recursive Convolutional Network for Image Super-Resolution," In Conference on Computer Vision and Pattern Recognition, pp. 1637-1645, 2016.
  14. C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, "Rethinking the Inception Architecture for Computer Vision," In Conference on Computer Vision and Pattern Recognition, pp. 2818-2826, 2016.
  15. K. Simonyan and A. Zisserman. "Very deep convolutional networks for large-scale image recognition," In International Conference on Learning Representations, 2015.
  16. W. Shi, J. Caballero, F. Huszar, J. Totz, A. P. Aitken, R. Bishop, D. Rueckert, and Z. Wang. "Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network," In Conference on Computer Vision and Pattern Recognition, pp. 1874-1883, 2016.
  17. H. Zhao, O. Gallo, J. Frosio, J. Kautz, "Loss functions for image restoration with neural networks," In Transactions on Computational Imaging, pp. 47-57, 2017.
  18. M. Bevilacqua, A. Roumy, C. Guillemot and M.-L. A. Morel, "Low-complexity single-image super-resolution based on nonnegative neighbor embedding," In Proceedings British Machine Vision Conference, 2012.
  19. R. Zeyde, M. Elad, and M. Protter, "On single image scale-up using sparse-representations," In International conference on Curves and Surfaces, pages 711-730, 2012.
  20. D. Martin, C. Fowlkes, D. Tal, and J. Malik, "A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics," In International Conference on Computer Vision, 2001.
  21. J.-B. Huang, A. Singh, and N. Ahuja. "Single Image Super-Resolution From Transformed Self-Exemplars," In Conference on Computer Vision and Pattern Recognition, pp. 5197-5206, 2015.