For years Single Image Super resolution(SISR) is an interesting and ill posed problem in Computer Vision. The traditional Super Resolution(SR) imaging approaches involve Interpolation, Reconstruction and Learning based methods. Interpolation methods are fast and uncomplicated to compute but they are not so accurate and reliable. Reconstruction based methods are better compared with Interpolation methods but are time consuming and quality degrades as the scaling increases. Even though, Learning based methods like Markov random chain are far better then all the previous they are unable to match the performance of deep learning models for SISR. In this project, Residual Dense Networks architecture proposed by Yhang et al \cite{srrdn} was extended to involve novel components and the importance of components in this architecture will be analysed. This architecture makes full use of hierarchial features from original low-resolution (LR) images to achieve higher performance. The network structure consists of four main blocks. The core of the architecture is the residual dense block(RDB) where the local features are extracted and made use of via dense convolutional layers. In this work, investigation of each block was performed and effect of each modules was be studied and analyzed. Analyses by use various loss metric was also carried out in this project. Also a comparison was made with various state of the art models which highly differ by architecture and components. The modules in the model were be built from scratch and were trained and tested. The training and testing was be carried out for various scaling factors and the performance was be evaluated.
View on arXiv