• Acta Optica Sinica
  • Vol. 41, Issue 7, 0730001 (2021)
Yong Li1, Qiuyu Jin1、2, Huaici Zhao2、*, and Bo Li3
Author Affiliations
  • 1School of Electrical Engineering, Shenyang University of Technology, Shenyang, Liaoning 110870, China
  • 2Key Laboratory of Optical-Electronics Information Processing, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, Liaoning 110016, China
  • 3College of Information, Shenyang Institute of Engineering, Shenyang, Liaoning 110136, China
  • show less
    DOI: 10.3788/AOS202141.0730001 Cite this Article Set citation alerts
    Yong Li, Qiuyu Jin, Huaici Zhao, Bo Li. Hyperspectral Image Reconstruction Based on Improved Residual Dense Network[J]. Acta Optica Sinica, 2021, 41(7): 0730001 Copy Citation Text show less
    Schematic of reconstruction process
    Fig. 1. Schematic of reconstruction process
    Schematic of RDSB
    Fig. 2. Schematic of RDSB
    Schematic of network structure
    Fig. 3. Schematic of network structure
    Reconstruction results of some images in ICVL dataset. (a)Algorithm in Ref. [11]; (b) algorithm in Ref. [12]; (c) algorithm in Ref. [17]; (d) algorithm in Ref. [18]; (e) proposed algorithm; (f) original RGB images
    Fig. 4. Reconstruction results of some images in ICVL dataset. (a)Algorithm in Ref. [11]; (b) algorithm in Ref. [12]; (c) algorithm in Ref. [17]; (d) algorithm in Ref. [18]; (e) proposed algorithm; (f) original RGB images
    Reconstruction results of different algorithms in CAVE dataset. (a) Algorithm in Ref. [11]; (b) algorithm in Ref. [12]; (c) algorithm in Ref. [17]; (d) algorithm in Ref. [18]; (e) proposed algorithm; (f) original images
    Fig. 5. Reconstruction results of different algorithms in CAVE dataset. (a) Algorithm in Ref. [11]; (b) algorithm in Ref. [12]; (c) algorithm in Ref. [17]; (d) algorithm in Ref. [18]; (e) proposed algorithm; (f) original images
    Reconstruction images on real-world images taken by an ordinal camera. (a) Algorithm in Ref. [11]; (b) algorithm in Ref. [12]; (c) algorithm in Ref. [17]; (d) algorithm in Ref. [18]; (e) proposed algorithm; (f) original RGB image
    Fig. 6. Reconstruction images on real-world images taken by an ordinal camera. (a) Algorithm in Ref. [11]; (b) algorithm in Ref. [12]; (c) algorithm in Ref. [17]; (d) algorithm in Ref. [18]; (e) proposed algorithm; (f) original RGB image
    IndicatorAlgorithm in Ref. [11]Algorithm in Ref. [12]Algorithm in Ref. [17]Algorithm in Ref. [18]Proposed algorithm
    MRAE0.06140.04350.04190.03310.0327
    RMSE2.6321.9561.7781.5061.452
    Table 1. Evaluate results of ICVL dataset
    DatasetAlgorithm in Ref.[11]Algorithm in Ref.[12]Algorithm in Ref.[17]Algorithm in Ref.[18]Proposed algorithm
    MRAERMSEMRAERMSEMRAERMSEMRAERMSEMRAERMSE
    Paints subset0.08875.3720.07554.5320.07424.3130.06674.3050.06414.295
    Food subset0.06753.2970.05243.1250.04892.8180.03652.6070.03832.536
    Real subset0.06173.1200.06313.3270.06013.5470.05793.0040.05822.974
    Skin subset0.08043.7810.06563.4980.06463.4140.06153.2620.06123.245
    Stuff subset0.09734.6680.07063.9640.07094.2360.06523.6820.06413.503
    Table 2. Evaluate results of CAVE dataset
    Yong Li, Qiuyu Jin, Huaici Zhao, Bo Li. Hyperspectral Image Reconstruction Based on Improved Residual Dense Network[J]. Acta Optica Sinica, 2021, 41(7): 0730001
    Download Citation