SwiftSRGAN - Rethinking Super-Resolution for Efficient and Real-time Inference

In recent years, there have been several advancements in the task of image super-resolution using the state of the art Deep Learning-based architectures. Many super-resolution-based techniques previously published, require high-end and top-of-the-line Graphics Processing Unit (GPUs) to perform image super-resolution. With the increasing advancements in Deep Learning approaches, neural networks have become more and more compute hungry. We took a step back and, focused on creating a real-time efficient solution. We present an architecture that is faster and smaller in terms of its memory footprint. The proposed architecture uses Depth-wise Separable Convolutions to extract features and, it performs on-par with other super-resolution GANs (Generative Adversarial Networks) while maintaining real-time inference and a low memory footprint. A real-time super-resolution enables streaming high resolution media content even under poor bandwidth conditions. We need a real-time and efficient solution for tasks like cloud gaming and media streaming but also not at the cost of using a high-end top-of-the-line GPU. While maintaining an efficient trade-off between the accuracy and latency, we are able to produce a comparable performance model which is one-eighth (1/8) the size of super-resolution GANs and computes 74 times faster than super-resolution GANs. This significant reduction in inference time enables us to perform super-resolution in real-time.