Image super-resolution reconstruction based on generative adversarial network model with double discriminators
- PDF / 5,210,408 Bytes
- 24 Pages / 439.37 x 666.142 pts Page_size
- 52 Downloads / 213 Views
Image super-resolution reconstruction based on generative adversarial network model with double discriminators Jinchao Huang 1 Received: 24 October 2019 / Revised: 14 July 2020 / Accepted: 4 August 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
To improve the reconstruction accuracy and efficiency for image super-resolution, this paper proposes a novel image super-resolution reconstruction algorithm based on generative adversarial network model with double discriminators (SRGAN-DD). For the proposed super-resolution reconstruction algorithm, we add a new discriminator based on SRGAN model, and combine the Kullback-Leibler (KL) divergence and reverse KL divergence as the uniform objective function to train such two discriminators. By using the complementary statistical characteristics from such two KL divergences, the proposed SRGAN-DD model will effectively disperse the estimated density in multiple modes, and the problem of network collapsed during reconstruction will be effectively avoided, so the robustness and efficiency of the model training is improved. For the part of model loss function design, the loss function to construct content loss by Charbonnier loss function is applied. Then, we design the perception loss and style loss by using the feature maps from middle layers of deep neural network models to achieve a combination loss function. At last, the deconvolutional operation is introduced into the network model for image reconstruction to reduce the reconstruction time complexity. To validate the feasibility and effectiveness, three groups of experiments are conducted to compare the proposed SRGAN-DD model with state-of-the-arts algorithms. Experimental results have shown that the proposed algorithm achieves the best performance on both objective and subjective judgment indicators. With the combination of loss function, the reconstructed images show less effect of artifacts and less influence of noises. The proposed SRGAN-DD model shows significant gains in perceived quality in reconstructing images. Keywords Image super-resolution reconstruction . Generative adversarial network . Double discriminators . KL divergence . Combination loss function
* Jinchao Huang [email protected]
1
College of Mathematics and Information Engineering, Longyan University, Longyan 364000 Fujian, China
Multimedia Tools and Applications
1 Introduction Image super-resolution (SR) reconstruction technology aims to recover a clear high-resolution image (HR) from a degraded low-resolution image (LR). Single frame image super-resolution reconstruction is widely used in security monitoring, satellite remote sensing image, and medical image processing. It has been a hot research issue in the field of computer vision. At present, the mainstream super-resolution reconstruction methods are interpolation based method [24, 45], reconstruction based method [25], and learning based method [4, 9, 12, 31, 32, 38]. Interpolation based method is a classical image restoration method. The main id
Data Loading...
