Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Laser & Optoelectronics Progress, Volume. 57, Issue 24, 241022(2020)

Blind Image Deblurring Based on Image Edge Determination Mechanism

Qing Qi1,2、*, Jichang Guo2, and Shanji Chen1
Author Affiliations
  • 1School of Physics and Electronic Information Engineering, Qinghai Nationalities University, Xining, Qinghai 810007, China
  • 2School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (13)
    Equations (0)
    References (28)
    Cited By (4)
    Tools
    Paper Information
    Topics
    Figures & Tables(13)
    Blurry image, clean image, and edge-weakened image. (a) Blurry image; (b) clean image; (c) edge-weakened image learned by PNet

    Fig. 1. Blurry image, clean image, and edge-weakened image. (a) Blurry image; (b) clean image; (c) edge-weakened image learned by PNet

    Download full size
    Structure of proposed network

    Fig. 2. Structure of proposed network

    Download full size
    Diagram of DNet subnet generator for image deblurring

    Fig. 3. Diagram of DNet subnet generator for image deblurring

    Download full size
    Dense residual block

    Fig. 4. Dense residual block

    Download full size
    Diagram of PNet subnet discriminator (PatchGAN) for image deblurring

    Fig. 5. Diagram of PNet subnet discriminator (PatchGAN) for image deblurring

    Download full size
    Results of image deblurring of compared methods on test dataset of GOPRO. (a) Blurry images; (b) method in Ref. [11]; (c) method in Ref. [13]; (d) method in Ref. [15]; (e) method in Ref. [16]; (f) ours

    Fig. 6. Results of image deblurring of compared methods on test dataset of GOPRO. (a) Blurry images; (b) method in Ref. [11]; (c) method in Ref. [13]; (d) method in Ref. [15]; (e) method in Ref. [16]; (f) ours

    Download full size
    Results of image deblurring of compared methods on dataset of K?hler. (a) Blurry images; (b) method in Ref. [11]; (c) method in Ref. [13]; (d) method in Ref. [15]; (e) method in Ref. [16]; (f) ours

    Fig. 7. Results of image deblurring of compared methods on dataset of K?hler. (a) Blurry images; (b) method in Ref. [11]; (c) method in Ref. [13]; (d) method in Ref. [15]; (e) method in Ref. [16]; (f) ours

    Download full size
    Results of deblurring of compared methods for real blurred images. (a) Blurry images;(b) method in Ref. [11]; (c) method in Ref. [13];(d) method in Ref. [15];(e) method in Ref. [16];(f) ours

    Fig. 8. Results of deblurring of compared methods for real blurred images. (a) Blurry images;(b) method in Ref. [11]; (c) method in Ref. [13];(d) method in Ref. [15];(e) method in Ref. [16];(f) ours

    Download full size
    Visual results of subnetworks on GOPRO test set. (a) Blurry input; results of (b) w/o content, (c) w/o edge, (d) w/o adv, (e) w/o PNet, and (f) proposed method

    Fig. 9. Visual results of subnetworks on GOPRO test set. (a) Blurry input; results of (b) w/o content, (c) w/o edge, (d) w/o adv, (e) w/o PNet, and (f) proposed method

    Download full size

    • Table 1. Quantitative evaluation results of proposed method and compared methods on GOPRO and K?hler datasets

      View table

      Table 1. Quantitative evaluation results of proposed method and compared methods on GOPRO and K?hler datasets

      MethodGOPROKöhler
      PSNRSSIMPSNRSSIM
      Method in Ref. [11]27.27780.818721.23710.6490
      Method in Ref. [13]28.32250.858821.23350.6525
      Method in Ref. [15]25.23630.777320.85070.6340
      Method in Ref. [16]27.80860.856419.08430.5838
      Ours29.22780.877921.29870.6544

    • Table 2. Quantitative evaluation results on dataset of GOPRO with different subnetworks

      View table

      Table 2. Quantitative evaluation results on dataset of GOPRO with different subnetworks

      MethodPSNRSSIM
      w/o PNet28.88560.8687
      Ours29.22780.8779

    • Table 3. Quantitative evaluation results on dataset of GOPRO for different loss functions

      View table

      Table 3. Quantitative evaluation results on dataset of GOPRO for different loss functions

      MethodPSNRSSIM
      w/o content26.57780.8034
      w/o edge28.42600.8418
      w/o adv28.58630.8513
      Ours29.22780.8779

    • Table 4. Quantitative evaluation results of proposed method and compared methods on dataset of GOPRO

      View table

      Table 4. Quantitative evaluation results of proposed method and compared methods on dataset of GOPRO

      MethodFLOPs /109Average time /s
      Method in Ref. [11]4.121300.0
      Method in Ref. [13]1760.048.1
      Method in Ref. [15]678.291.1
      Method in Ref. [16]411.340.7
      Ours628.031.3
    Tools

    Get Citation

    Copy Citation Text

    Qing Qi, Jichang Guo, Shanji Chen. Blind Image Deblurring Based on Image Edge Determination Mechanism[J]. Laser & Optoelectronics Progress, 2020, 57(24): 241022

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Set citation alerts for article
    Save article for my favorites
    Paper Information

    Category: Image Processing

    Received: Jun. 1, 2020

    Accepted: Jun. 28, 2020

    Published Online: Nov. 23, 2020

    The Author Email: Qi Qing (qiqing@tju.edu.cn)

    DOI:10.3788/LOP57.241022

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology