edge-SR: Super-Resolution For The Masses

TL;DR

This paper introduces edge-SR, a set of simple, interpretable one-layer deep learning architectures designed for real-time image super-resolution on edge devices, bridging the gap between classic upscalers and complex deep learning models.

Contribution

Proposes edge-SR, a novel one-layer architecture for image super-resolution optimized for edge devices, balancing quality and speed, and enhancing interpretability compared to existing methods.

Findings

edge-SR achieves faster performance than deep models on edge hardware.

It offers a better trade-off between image quality and runtime.

The architecture provides interpretability for understanding super-resolution strategies.

Abstract

Classic image scaling (e.g. bicubic) can be seen as one convolutional layer and a single upscaling filter. Its implementation is ubiquitous in all display devices and image processing software. In the last decade deep learning systems have been introduced for the task of image super-resolution (SR), using several convolutional layers and numerous filters. These methods have taken over the benchmarks of image quality for upscaling tasks. Would it be possible to replace classic upscalers with deep learning architectures on edge devices such as display panels, tablets, laptop computers, etc.? On one hand, the current trend in Edge-AI chips shows a promising future in this direction, with rapid development of hardware that can run deep-learning tasks efficiently. On the other hand, in image SR only few architectures have pushed the limit to extreme small sizes that can actually run on edge devices at real-time. We explore possible solutions to this problem with the aim to fill the gap between classic upscalers and small deep learning configurations. As a transition from classic to deep-learning upscaling we propose edge-SR (eSR), a set of one-layer architectures that use interpretable mechanisms to upscale images. Certainly, a one-layer architecture cannot reach the quality of deep learning systems. Nevertheless, we find that for high speed requirements, eSR becomes better at trading-off image quality and runtime performance. Filling the gap between classic and deep-learning architectures for image upscaling is critical for massive adoption of this technology. It is equally important to have an interpretable system that can reveal the inner strategies to solve this problem and guide us to future improvements and better understanding of larger networks.