This work explores the task of super-resolution using advanced GAN-based architectures which are tailored specifically for this purpose. A primary focus lies within the notion of addressing the inherent challenges of the ill-posed nature of super-resolution by incorporating synthetic images in various ways, emphasizing the importance of model selections that integrate such synthetic image approaches. Based on this characteristic, it investigates the relationship between super-resolution and related image reconstruction tasks such as image deblurring and low-light image enhancement through transfer learning. The experiments reveal the capabilities of state-of-the-art super-resolution models while also highlighting their potential and limitations, particularly in handling deblurring and low-light scenarios. Despite their high performance in super-resolution, these models still struggle with the complexities of upscaling processes inherent in these latter tasks, underscoring the necessity for pretraining on specialized datasets to address these challenges effectively. This study contributes insights into the strengths and limitations of advanced super-resolution techniques while emphasizing the importance of specialized training for addressing specific image enhancement tasks.