An efficient image super resolution model with dense skip connections between complex filter structures in Generative Adversarial Networks. (30th December 2021)

• Record Type: Journal Article
• Authors: Sharma, Shailza; Kumar, Vinay
• Is Part Of: Expert systems with applications. Volume 186(2021)
• Publication Date: 2021-12-30
• Subjects: Super resolution -- Convolutional neural networks -- Generative adversarial networks -- Inception architecture -- Subpixel layer; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2021.115780
• Languages: English
• ISSNs: 0957-4174

Abstract

Abstract: Generative Adversarial Network (GAN) based models have gained a lot of popularity due to their outstanding performance in image super resolution tasks. However, these networks have few inherent problems; such as, high computational complexity, large depth and vanishing gradient. Present work proposes a novel GAN based architecture, namely, Super Resolution with Inception Network (SRINet) to solve the above mentioned problems. Generator architecture of SRINet uses complex filter structure rather than the linear filter structure to increase the depth and width of network without increasing the computational cost. Complex filter settings, present in the architecture, helps it to attain locally distributed information along with hierarchical global information in an image. Hence, the proposed method approximates the most favorable sparse structures to foster the learning capability of network. Additionally, progressive two stage upscaling approach with dense skip connections are introduced in the generator architecture. This technique helps the proposed network to learn precise mapping to generate an output image from the low resolution image. To measure visual quality of an image, we use human visual system based visual information fidelity metric. Proposed method outperforms all the state-of-the-art methods qualitatively (perceptually) and quantitatively on other GAN based methods. Highlights: Proposed an Generative Adversarial Network based model for image super resolution. Primitive and hierarchical feature learning with Complex filter structure. Dense skip connections are introduced to increase the learning capability. Progressive upscaling approach is used to obtain fine texture details. Performance is evaluated with the state-of-the-art methods.