• Laser & Optoelectronics Progress
  • Vol. 61, Issue 18, 1837001 (2024)
Ruihong Wen1,2,3, Chunyu Liu1,3,*, Shuai Liu1,3, Meili Zhou1,3, and Yuxin Zhang1,3
Author Affiliations
  • 1Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, Jilin, China
  • 2University of Chinese Academy of Sciences, Beijing 100049, China
  • 3Key Laboratory of Space-based Dynamic & Rapid Optical Imaging Technology, Chinese Academy of Sciences,Changchun 130033, Jilin, China
  • show less
    DOI: 10.3788/LOP232552 Cite this Article Set citation alerts
    Ruihong Wen, Chunyu Liu, Shuai Liu, Meili Zhou, Yuxin Zhang. Detail-Preserving Multi-Exposure Image Fusion Based on Adaptive Weight[J]. Laser & Optoelectronics Progress, 2024, 61(18): 1837001 Copy Citation Text show less
    Relationship between image information entropy and exposure time in low dynamic range scene
    Fig. 1. Relationship between image information entropy and exposure time in low dynamic range scene
    Comparison before and after guided filtering
    Fig. 2. Comparison before and after guided filtering
    The process of proposed method
    Fig. 3. The process of proposed method
    Laplace pyramid reconstruction
    Fig. 4. Laplace pyramid reconstruction
    Partial fusion results of proposed algorithm
    Fig. 5. Partial fusion results of proposed algorithm
    Fusion results of source image sequence Cave by different algorithms. (a) Multi-exposure image sequence Cave; (b) algorithm 1; (c) algorithm 2; (d) algorithm 3; (e) algorithm 4; (f) algorithm 5; (g) algorithm 6; (h) algorithm 7; (i) proposed algorithm
    Fig. 6. Fusion results of source image sequence Cave by different algorithms. (a) Multi-exposure image sequence Cave; (b) algorithm 1; (c) algorithm 2; (d) algorithm 3; (e) algorithm 4; (f) algorithm 5; (g) algorithm 6; (h) algorithm 7; (i) proposed algorithm
    Fusion results of source image sequence Lamp by different algorithms. (a) Multi-exposure image sequence Lamp(b) algorithm 1; (c) algorithm 2;(d) algorithm 3; (e) algorithm 4; (f) algorithm 5; (g) algorithm 6; (h) algorithm 7; (i) proposed algorithm
    Fig. 7. Fusion results of source image sequence Lamp by different algorithms. (a) Multi-exposure image sequence Lamp(b) algorithm 1; (c) algorithm 2;(d) algorithm 3; (e) algorithm 4; (f) algorithm 5; (g) algorithm 6; (h) algorithm 7; (i) proposed algorithm
    Fusion results of source image sequence Mountain Garden by different algorithms. (a) Multi-exposure image sequence Mountain garden; (b) algorithm 1;(c) algorithm 2; (d) algorithm 3; (e) algorithm 4; (f) algorithm 5; (g) algorithm 6; (h) algorithm 7; (i) proposed algorithm
    Fig. 8. Fusion results of source image sequence Mountain Garden by different algorithms. (a) Multi-exposure image sequence Mountain garden; (b) algorithm 1;(c) algorithm 2; (d) algorithm 3; (e) algorithm 4; (f) algorithm 5; (g) algorithm 6; (h) algorithm 7; (i) proposed algorithm
    Fusion and ablation experimental results of multi-exposure image sequence Venice. (a) Multi-exposure image sequence Venice; (b) fusion result of proposed algorithm; (c) fusion result without guided filtering; (d) fusion result without structural weight; (e) fusion result without saturation weight; (f) fusion result without exposure weight
    Fig. 9. Fusion and ablation experimental results of multi-exposure image sequence Venice. (a) Multi-exposure image sequence Venice; (b) fusion result of proposed algorithm; (c) fusion result without guided filtering; (d) fusion result without structural weight; (e) fusion result without saturation weight; (f) fusion result without exposure weight
    Relationship between MEF-SSIM and Gaussian standard deviation
    Fig. 10. Relationship between MEF-SSIM and Gaussian standard deviation
    DatasetEvaluationAlgorithm
    1234567Proposed
    Dataset 1MEF-SSIM0.9790.9720.9830.9780.9660.9830.9750.983
    CE1.8841.7071.6591.6511.6071.9191.8111.944
    Dataset 2MEF-SSIM0.9740.9330.9790.9230.9560.9780.9680.977
    CE2.3442.2492.0982.2112.0952.4172.3312.479
    Dataset 3MEF-SSIM0.9870.9620.9880.9640.9710.9870.9800.988
    CE2.5982.4752.1732.3211.8352.2162.1802.601
    Table 1. Comparison of objective indicator average values of different algorithms on three datasets
    DatasetMEF-SSIMCE
    SEGCEGCSGCSECSEGSEGCEGCSGCSECSEG
    Dataset 10.9750.9810.9820.9820.9831.8121.9121.8741.8971.944
    Dataset 20.9690.9740.9760.9770.9772.2272.4692.4372.4712.479
    Dataset 30.9780.9850.9860.9870.9882.5522.5072.5172.5992.601
    Table 2. Comparison of indicators for different element combinations in three datasets
    Ruihong Wen, Chunyu Liu, Shuai Liu, Meili Zhou, Yuxin Zhang. Detail-Preserving Multi-Exposure Image Fusion Based on Adaptive Weight[J]. Laser & Optoelectronics Progress, 2024, 61(18): 1837001
    Download Citation