Fig. 1. Network structure of proposed generator
Fig. 2. Residual block in the generator network
Fig. 3. Discriminator network structure
Fig. 4. Different images. (a) River and car of normal-light images; (b) images with illuminance of 0.2; (c) images with illuminance of 0.35; (d) images with illuminance of 0.5; (e) HSV color space images with illuminance of 0.2; (f) H component; (g) S component; (h) V component
Fig. 5. Flow chart of proposed algorithm
Fig. 6. Enhanced results of low-light image Starfish by different algorithms. (a) Low-light image; (b) normal-light image; (c) Ref. [6] algorithm; (d) Ref. [7] algorithm; (e) Ref. [8] algorithm; (f) Ref. [9] algorithm; (g) Ref. [10] algorithm; (h) Ref. [11] algorithm; (i) Ref. [12] algorithm; (j) proposed algorithm
Fig. 7. Enhanced results of low-light image Man by different algorithms. (a) Low-light image; (b) normal-light image; (c) Ref. [6] algorithm; (d) Ref. [7] algorithm; (e) Ref. [8] algorithm; (f) Ref. [9] algorithm; (g) Ref. [10] algorithm; (h) Ref. [11] algorithm; (i) Ref. [12] algorithm; (j) proposed algorithm
Fig. 8. Enhanced results of low-light image Street by different algorithms. (a) Low-light image; (b) normal-light image; (c) Ref. [6] algorithm; (d) Ref. [7] algorithm; (e) Ref. [8] algorithm; (f) Ref. [9] algorithm; (g) Ref. [10] algorithm; (h) Ref. [11] algorithm; (i) Ref. [12] algorithm; (j) proposed algorithm
Fig. 9. Enhancement results of real low-light image Pocky by different algorithms. (a) Real low-light image; (b) Ref. [6] algorithm; (c) Ref. [7] algorithm; (d) Ref. [8] algorithm; (e) Ref. [9] algorithm; (f) Ref. [10] algorithm; (g) Ref. [11] algorithm; (h) Ref. [12] algorithm; (i) proposed algorithm
Fig. 10. Enhancement results of real low-light image Palace by different algorithms. (a) Real low-light image; (b) Ref. [6] algorithm; (c) Ref. [7] algorithm; (d) Ref. [8] algorithm; (e) Ref. [9] algorithm; (f) Ref. [10] algorithm; (g) Ref. [11] algorithm; (h) Ref. [12] algorithm; (i) proposed algorithm
Fig. 11. Comparison results of different algorithms. (a) Average; (b) average gradient
Fig. 12. Subjective comparison of low-light image enhancement results by generator network and generative adversarial network. (a) Low-light image; (b) normal-light image; (c) results of generator network; (d) results of generative adversarial network
Fig. 13. Comparison results of generator network and generative adversarial network of different images. (a) PSNR; (b) SSIM
Image | Evaluationindex | Method |
---|
Ref. [6] | Ref. [7] | Ref. [8] | Ref. [9] | Ref. [10] | Ref. [11] | Ref. [12] | Proposed |
---|
Starfish | PSNR /dB | 17.5299 | 21.5799 | 18.5596 | 14.8139 | 15.1619 | 14.9161 | 23.7331 | 24.6770 | | SSIM | 0.8844 | 0.9087 | 0.7974 | 0.7963 | 0.7354 | 0.7767 | 0.9233 | 0.9301 | Bridge | PSNR /dB | 18.7698 | 19.6941 | 19.4387 | 15.1122 | 16.0498 | 17.3796 | 22.7277 | 24.1884 | | SSIM | 0.7804 | 0.8004 | 0.7134 | 0.6370 | 0.6663 | 0.7511 | 0.7864 | 0.8156 | Man | PSNR /dB | 20.1773 | 16.8662 | 17.3650 | 18.2481 | 18.8261 | 19.5051 | 16.9811 | 23.0426 | | SSIM | 0.8655 | 0.8069 | 0.7902 | 0.8339 | 0.8139 | 0.8689 | 0.8260 | 0.9097 | Boat | PSNR /dB | 16.6960 | 20.1897 | 18.1177 | 13.3807 | 13.9680 | 16.6876 | 22.3434 | 22.6587 | | SSIM | 0.8079 | 0.8272 | 0.7564 | 0.6626 | 0.6914 | 0.8260 | 0.8498 | 0.8643 | Street | PSNR /dB | 17.5108 | 19.3502 | 18.1892 | 15.7510 | 15.9564 | 20.4417 | 18.6525 | 25.6980 | | SSIM | 0.8682 | 0.8755 | 0.7887 | 0.8037 | 0.7586 | 0.8952 | 0.8816 | 0.9387 |
|
Table 1. PSNR and SSIM of different algorithms