Researching

Journals
  • Advanced Photonics
  • Photonics Insights
  • Advanced Photonics Nexus
  • Photonics Research
  • Advanced Imaging
  • View All Journals
  • Chinese Optics Letters
  • High Power Laser Science and Engineering
    • Articles
  • Optics
  • Physics
  • Geography
  • View All Subjects
    • Conferences
  • CIOP
  • HPLSE
  • AP
  • View All Events
    • News
    About CLP
    Search by keywords or author
    Journals >Laser & Optoelectronics Progress >Volume 60 >Issue 16 >Page 1633001 > Article
    • Laser & Optoelectronics Progress
    • Vol. 60, Issue 16, 1633001 (2023)
    Mural Style Transfer with Feature Clustering and Deep Residual Shrinkage Network
    Meng Wu1,*, Yining Gao1, and Jia Wang2
    Author Affiliations
  • 1School of Information and Control Engineering, Xi'an University of Architecture and Technology, Xi'an 710055, Shaanxi, China
  • 2Shaanxi History Museum, Xi'an 710061, Shaanxi, China
    • show less
    DOI: 10.3788/LOP222583 Cite this Article Set citation alerts
    Meng Wu, Yining Gao, Jia Wang. Mural Style Transfer with Feature Clustering and Deep Residual Shrinkage Network[J]. Laser & Optoelectronics Progress, 2023, 60(16): 1633001 Copy Citation Text show less
    Network framework
    Fig. 1. Network framework
    Download full size
    Algorithm flow
    Fig. 2. Algorithm flow
    Download full size
    Cluster graph comparison. (a) Input image; (b) VGG19 space; (c) RGB space
    Fig. 3. Cluster graph comparison. (a) Input image; (b) VGG19 space; (c) RGB space
    Download full size
    Algorithm flow
    Fig. 4. Algorithm flow
    Download full size
    Color space comparison. (a) Input image; (b) RGB space; (c) LAB space
    Fig. 5. Color space comparison. (a) Input image; (b) RGB space; (c) LAB space
    Download full size
    RSB structure
    Fig. 6. RSB structure
    Download full size
    Soft threshold function and its derivative. (a) Soft threshold function; (b) soft threshold function derivative
    Fig. 7. Soft threshold function and its derivative. (a) Soft threshold function; (b) soft threshold function derivative
    Download full size
    Image representation of different network levels. (a) Original image; (b) Conv_1_1; (c) Conv_2_1; (d) Conv_3_1; (e) Conv_4_1
    Fig. 8. Image representation of different network levels. (a) Original image; (b) Conv_1_1; (c) Conv_2_1; (d) Conv_3_1; (e) Conv_4_1
    Download full size
    RSB validity verification. (a) Content image; (b) without RSB; (c) with RSB
    Fig. 9. RSB validity verification. (a) Content image; (b) without RSB; (c) with RSB
    Download full size
    The effect of style transfer with different cluster numbers. (a) Input image; (b) K=1; (c) K=3; (d) K=5; (e) K=10
    Fig. 10. The effect of style transfer with different cluster numbers. (a) Input image; (b) K=1; (c) K=3; (d) K=5; (e) K=10
    Download full size
    The effect of style transfer with different fusion coefficients. (a) Input image; (b) αk= 0.2; (c) αk= 0.6; (d) αk=1.0
    Fig. 11. The effect of style transfer with different fusion coefficients. (a) Input image; (b) αk= 0.2; (c) αk= 0.6; (d) αk=1.0
    Download full size
    The effect of style transfer with different coverage ratios. (a) Input image; (b) coverage ratio is 0.25; (c) coverage ratio is 0.5; (d) coverage ratio is 1.0
    Fig. 12. The effect of style transfer with different coverage ratios. (a) Input image; (b) coverage ratio is 0.25; (c) coverage ratio is 0.5; (d) coverage ratio is 1.0
    Download full size
    Comparison of different style transfer methods. (a) Content images; (b) style images; (c) method of reference [5]; (d) AdaIN; (e) SANet; (f) MST; (g) proposed method
    Fig. 13. Comparison of different style transfer methods. (a) Content images; (b) style images; (c) method of reference [5]; (d) AdaIN; (e) SANet; (f) MST; (g) proposed method
    Download full size
    Comparison results of different data augmentation methods. (a) Original image; (b) flip horizontal; (c) rotate 90°; (d) rotate 180°; (e) rotate 270°; (f) contrast; (g) color enhancement; (h) brightness enhancement
    Fig. 14. Comparison results of different data augmentation methods. (a) Original image; (b) flip horizontal; (c) rotate 90°; (d) rotate 180°; (e) rotate 270°; (f) contrast; (g) color enhancement; (h) brightness enhancement
    Download full size
    Effect of different dataset generation. (a) Original murals; (b) masked images; (c) real; (d) real+s.a.; (e) synthetic; (f) real+synthetic
    Fig. 15. Effect of different dataset generation. (a) Original murals; (b) masked images; (c) real; (d) real+s.a.; (e) synthetic; (f) real+synthetic
    Download full size
    ImageMethodMSSIMRPSNREMSE /103
    picture1Method of reference［5］0.569.307.65
    AdaIN0.589.038.13
    SANet0.527.387.15
    MST0.459.207.82
    Proposed method0.6411.254.88
    picture2Method of reference［5］0.4812.813.40
    AdaIN0.5113.193.12
    SANet0.3711.884.21
    MST0.3911.624.48
    Proposed method0.5314.692.21
    picture3Method of reference［5］0.5315.641.76
    AdaIN0.4815.251.94
    SANet0.3414.362.38
    MST0.3413.672.79
    Proposed method0.5516.101.59
    picture4Method of reference［5］0.4315.781.24
    AdaIN0.3817.851.15
    SANet0.2816.451.47
    MST0.3416.711.38
    Proposed method0.4518.251.13
    Table 1. Quantitative statistical results of stylized test
    MethodRunning time /s
    AdaIN0.40
    SANet0.89
    MST4.77
    Proposed method1.65
    Table 2. Comparison of average generation time of different methods
    MethodMSSIMRPSNREMSE /103
    AdaIN0.4318.762.68
    SANet0.4118.222.94
    MST0.3817.783.52
    Proposed method0.4919.262.31
    Table 3. Mural digital generation results
    Abstract
    Get PDF(in Chinese)
    Figures&Tables (18)
    Equations (13)
    References (20)
    Get Citation
    Copy Citation Text
    Meng Wu, Yining Gao, Jia Wang. Mural Style Transfer with Feature Clustering and Deep Residual Shrinkage Network[J]. Laser & Optoelectronics Progress, 2023, 60(16): 1633001
    Download Citation
    Set citation alerts for the article
    Tools
    Share
    Set citation alerts for the article
    Save the article for my favorites
    Paper Information
    Recommended Topics
    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology