Acta Optica Sinica, Volume. 45, Issue 15, 1510002(2025)

Attention-Guided Matching for Stereo Multi-Focus Image Fusion

Sicheng Jiang, Xiaodong Chen*, Huaiyu Cai, and Yi Wang
Author Affiliations
  • Key Laboratory of Optoelectronics Information Technology, Ministry of Education, School of Precision Instrument and Optoelectronics Engineering, Tianjin University, Tianjin 300072, China
  • show less
    Figures & Tables(11)
    Framework of proposed method. (a) Feature extraction; (b) feature matching; (c) feature fusion; (d) feature reconstruction
    Architecture of encoder/decoder components. (a) CNN encoder; (b) Transformer encoder; (c) decoder
    Workflow of modality alignment using Q-Former
    Architecture of match module
    Architecture of fusion module
    Experimental dataset samples. (a) Original clear monocular images; (b) monocular near-focused images; (c) monocular far-focused images; (d) stereo multi-focus images, left view; (e) stereo multi-focus images, right view; (f) random masks
    Comparative results of monocular multi-focus image fusion
    Comparative results of stereo multi-focus image fusion
    • Table 1. Quantitative results of monocular multi-focus image fusion

      View table

      Table 1. Quantitative results of monocular multi-focus image fusion

      MetricsNSCT-SRGFDSIFTMFCNNIFCNNOurs
      AG4.83734.84534.86354.87204.85224.9151
      GLD9.44559.51749.67329.47659.833610.1928
      NMI0.84630.87150.95830.91720.93561.1034
      VIFF0.95390.94550.95480.95230.98060.9773
      QAB/F0.73180.68540.72090.76630.76890.7894
    • Table 2. Quantitative results of monocular multi-focus image fusion

      View table

      Table 2. Quantitative results of monocular multi-focus image fusion

      MetricsNSCT-SRNSCT-SR*DSIFTIFCNNIFCNN*Ours
      AG6.65826.70296.78157.18017.23357.5258
      GLD11.043911.155311.251611.377711.516211.8949
      NMI0.87910.90650.89680.93361.06581.2104
      VIFF0.83040.86640.85900.89790.96440.9813
      NAB/F0.18370.15310.14720.15810.12870.0715
    • Table 3. Ablation study results

      View table

      Table 3. Ablation study results

      MetricsBaselinew/o matchw/o fusion
      MonoStereoMonoStereoMonoStereo
      NMI1.10341.21041.09750.96521.02170.9853
      VIFF0.97730.98130.97820.92840.96330.9576
      QAB/F0.78940.78670.7624
      NAB/F0.07150.15120.1025
    Tools

    Get Citation

    Copy Citation Text

    Sicheng Jiang, Xiaodong Chen, Huaiyu Cai, Yi Wang. Attention-Guided Matching for Stereo Multi-Focus Image Fusion[J]. Acta Optica Sinica, 2025, 45(15): 1510002

    Download Citation

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

    Category: Image Processing

    Received: Apr. 3, 2025

    Accepted: Apr. 27, 2025

    Published Online: Aug. 15, 2025

    The Author Email: Xiaodong Chen (xdchen@tju.edu.cn)

    DOI:10.3788/AOS250836

    CSTR:32393.14.AOS250836

    Topics