Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Image compact-resolution and reconstruction using reversible network

  • Author(s): Jieming Yang 1, 2 ; Hongwei Ge 1, 2 ; Jinlong Yang 1, 2 ; Yubing Tong 3
    • View affiliations
  • Source: Volume 14, Issue 16, 19 December 2020, p. 4376 – 4384
    DOI:  10.1049/iet-ipr.2019.1652 , Print ISSN 1751-9659, Online ISSN 1751-9667
© The Institution of Engineering and Technology
Received 12/12/2019, Accepted 30/11/2020, Revised 26/11/2020, Published 14/12/2020

The dual problem of image super-resolution (SR), which is referred to as compact-resolution (CR), and the corresponding image reconstruction are studied. These two problems have been studied independently by the researchers. In this study, a novel model for image CR and the corresponding reconstruction using the reversible network has been proposed. The reversible network has two properties, the first property, lossless information forwarding, which makes the compact-resolved image retain more information from the original HR image. The second property, bidirectional mapping, by which the forward and reverse propagation of a reversible network can be utilised to implement image CR and reconstruction, respectively, i.e. using the reverse process of image CR to guide the reconstruction. In addition, the utilisation of a reversible network may reduce the size of the model. The superiority of the proposed model was demonstrated by comparing its performance with the state-of-the-art methods on four well-known benchmark datasets.

Inspec keywords: image resolution; image reconstruction

Other keywords: forward propagation; image reconstruction; reverse propagation; image compact-resolution; compact-resolved image; HR image; lossless information forwarding; image super-resolution; reverse process; reversible network; bidirectional mapping; image CR

Subjects: Computer vision and image processing techniques; Optical, image and video signal processing

References

    1. 1)
      • 2. Kopf, J., Shamir, A., Peers, P.: ‘Content-adaptive image downscaling’, ACM Trans. Graph., 2013, 32, (6), pp. 1–8.
    2. 2)
      • 7. Dong, C., Loy, C.C., He, K., et al: ‘Learning a deep convolutional network for image super-resolution’. European Conf. on Computer Vision, Zurich, Switzerland, 2014, pp. 184–199.
    3. 3)
      • 10. Lim, B., Son, S., Kim, H., et al: ‘Enhanced deep residual networks for single image super-resolution’. Proc. IEEE Conf. Computer Vision and Pattern Recognition Workshops, Honolulu, HI, USA, 2017, pp. 136–144.
    4. 4)
      • 28. Dinh, L., Krueger, D., Bengio, Y.: ‘Nice: non-linear independent components estimation’, arXiv preprint arXiv:., 2014.
    5. 5)
      • 32. Jacobsen, J.-H., Smeulders, A., Oyallon, E.: ‘I-Revnet: deep invertible networks’, arXiv preprint arXiv:.07088, 2018.
    6. 6)
      • 34. Van der Ouderaa, T.F., Worrall, D.E.: ‘Reversible gans for memory-efficient image-to-image translation’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, Los Angeles, CA, USA, 2019, pp. 4720–4728.
    7. 7)
      • 11. Yu, J., Fan, Y., Yang, J., et al: ‘Wide activation for efficient and accurate image super-resolution’, arXiv preprint arXiv:.08718, 2018.
    8. 8)
      • 12. Jiang, F., Tao, W., Liu, S., et al: ‘An end-to-end compression framework based on convolutional neural networks’, IEEE Trans. Circuits Syst. Video Technol., 2017, 28, (10), pp. 3007–3018.
    9. 9)
      • 29. Dinh, L., Sohl-Dickstein, J., Bengio, S.: ‘Density estimation using real nvp’, arXiv preprint arXiv:.08803, 2016.
    10. 10)
      • 26. Salimans, T., Kingma, D.P.: ‘Weight normalization: A simple reparameterization to accelerate training of deep neural networks’. Proc. Advances in Neural Information Processing Systems, Barcelona, Spain, 2016, pp. 901–909.
    11. 11)
      • 36. Zeyde, R., Elad, M., Protter, M.: ‘On single image scale-up using sparse-representations’. Int. Conf. on Curves and Surfaces, Avignon, France, 2010, pp. 711–730.
    12. 12)
      • 16. Fang, L., Au, O.: ‘Subpixel-based image down-sampling with min-max directional error for stripe display’, IEEE J. Sel. Top. Signal Process., 2010, 5, (2), pp. 240–251.
    13. 13)
      • 3. Oeztireli, A.C., Gross, M.: ‘Perceptually based downscaling of images’, ACM Trans. Graph., 2015, 34, (4), pp. 1–10.
    14. 14)
      • 24. Goodfellow, I., Pouget-Abadie, J., Mirza, M., et al: ‘Generative adversarial nets’. Proc. Advances in Neural Information Processing Systems, Montreal, Canada, 2014, pp. 2672–2680.
    15. 15)
      • 30. Kingma, D.P., Dhariwal, P.: ‘Glow: generative flow with invertible 1 × 1 convolutions’. Proc. Advances in Neural Information Processing Systems, Montreal, Canada, 2018, pp. 10215–10224.
    16. 16)
      • 21. Vaquero, D., Turk, M., Pulli, K., et al: ‘A survey of image retargeting techniques’. Applications of Digital Image Processing XXXIII, Int. Society for Optics and Photonics, 2010, 31, 1, pp. 1–6.
    17. 17)
      • 25. Ioffe, S., Szegedy, C.: ‘Batch normalization: accelerating deep network training by reducing internal covariate shift’, arXiv preprint arXiv:.03167, 2015.
    18. 18)
      • 27. Maclaurin, D., Duvenaud, D., Adams, R.: ‘Gradient-based hyperparameter optimization through reversible learning’. Proc. Internat. Conf. Mach. Learn, Miami, FL, USA, 2015, pp. 2113–2122.
    19. 19)
      • 18. Avidan, S., Shamir, A.: ‘Seam carving for content-aware image resizing’, ACM Trans. Graph., 2007, 26, (3), pp. 10–20.
    20. 20)
      • 35. Bevilacqua, M., Roumy, A., Guillemot, C., et al: ‘Low-complexity single-image super-resolution based on nonnegative neighbor embedding’, 2012.
    21. 21)
      • 14. Daly, S.: ‘47.3: analysis of subtriad addressing algorithms by visual system models’. SID Symp. Digest of Technical Papers, 2001, 32, (1), pp. 1200–1203.
    22. 22)
      • 6. Yang, J., Wright, J., Huang, T.S., et al: ‘Image super-resolution via sparse representation’, IEEE Trans. Image Process, 2010, 19, (11), pp. 2861–2873.
    23. 23)
      • 22. Lu, W.-S., Sevcenco, A.-M.: ‘Design of optimal decimation and interpolation filters for low bit-rate image coding’. APCCAS 2006–2006 IEEE Asia Pacific Conf. on Circuits and Systems, Singapore, 2006, pp. 378–381.
    24. 24)
      • 17. Fang, L., Au, O.C., Tang, K., et al: ‘Novel 2-D mmse subpixel-based image down-sampling’, IEEE Trans. Circuits Syst. Video Technol., 2011, 22, (5), pp. 740–753.
    25. 25)
      • 8. Kim, J., Kwon Lee, J., Mu Lee, K.: ‘Accurate image super-resolution using very deep convolutional networks’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016, pp. 1646–1654.
    26. 26)
      • 1. Mitchell, D.P., Netravali, A.: ‘Reconstruction filters in computer-graphics’, SIGGRAPH Comput. Graph., 1988, 22, (4), pp. 221–228.
    27. 27)
      • 4. Wang, Z., Bovik, A.C., Sheikh, H.R., et al: ‘Image quality assessment: from error visibility to structural similarity’, IEEE Trans. Image Process, 2004, 13, (4), pp. 600–612.
    28. 28)
      • 20. Setlur, V., Takagi, S., Raskar, R., et al: ‘Automatic image retargeting’. Proc. of the 4th Int. Conf. On Mobile And Ubiquitous Multimedia, Christchurch, New Zealand, 2005, pp. 59–68.
    29. 29)
      • 13. Li, Y., Liu, D., Li, H., et al: ‘Learning a convolutional neural network for image compact-resolution’, IEEE Trans. Image Process, 2018, 28, (3), pp. 1092–1107.
    30. 30)
      • 5. Liu, J., He, S., Lau, R.W.H.: ‘L_0-regularized image downscaling’, IEEE Trans. Image Process, 2017, 27, (3), pp. 1076–1085.
    31. 31)
      • 15. Daly, S.J., Kovvuri, R.R.K.: ‘Methods and systems for improving display resolution in images using sub-pixel sampling and visual error filtering’, U.S. Patent No. 6,608,632, 19 Aug. 2003.
    32. 32)
      • 38. Yang, C.-Y., Yang, M.-H.: ‘Fast direct super-resolution by simple functions’. IEEE Conf. Computer Vision and Pattern Recognition, Portland, OR, USA, 2013, pp. 561–568.
    33. 33)
      • 9. Ledig, C., Theis, L., Huszár, F., et al: ‘Photo-realistic single image super-resolution using a generative adversarial network’. Proc. IEEE Conf. Computer Vision and Pattern Recognition n, Honolulu, HI, USA, 2017, pp. 4681–4690.
    34. 34)
      • 37. Huang, J.-B., Singh, A., Ahuja, N.: ‘Single image super-resolution from transformed self-exemplars’. IEEE Conf. Computer Vision and Pattern Recognition, Boston, MA, USA, 2015, pp. 5197–5206.
    35. 35)
      • 19. Rubinstein, M., Gutierrez, D., Sorkine, O., et al: ‘A comparative study of image retargeting’, ACM Trans. Graph., 2010, 29, (6), pp. 1–10.
    36. 36)
      • 31. Grover, A., Dhar, M., Ermon, S.: ‘Flow-gan: combining Maximum likelihood and adversarial learning in generative models’, arXiv preprint arXiv:.08868, 2017.
    37. 37)
      • 33. Gomez, A.N., Ren, M., Urtasun, R., et al: ‘The reversible residual network: backpropagation without storing activations’. Proc. Advances in Neural Information Processing Systems, Los Angeles, CA, USA, 2017, pp. 2214–2224.
    38. 38)
      • 23. Tsaig, Y., Elad, M., Milanfar, P., et al: ‘Variable projection for near-optimal filtering in low bit-rate block coders’, IEEE Trans. Circuits Syst. Video Technol., 2005, 15, (1), pp. 154–160.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2019.1652
Loading

Related content

content/journals/10.1049/iet-ipr.2019.1652
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address