EHT-SR: An Entropy-Based Hybrid Approach for Faster Super-Resolution
Author(s)
Dharmavarapu, Abhilash
Advisor(s)
Editor(s)
Collections
Supplementary to:
Permanent Link
Abstract
Deep neural networks have produced tremendous advancements in Super-Resolution (SR) results. These improvements often come at the cost of inference latency, which is particularly important in low-resource devices. This paper, therefore, proposes a novel method to optimize the inference latency of SR models, called EHT-SR (Entropy-Based Hybrid Tiled SR), which leverages both accurate but slow DNN-based methods and a simple but fast bicubic interpolation for super-resolution. Particularly, we observe that a lightweight bicubic interpolation can still provide good image super-resolution quality for selected regions of the input image. An entropy-based heuristic, which we derive from a rigorous analysis of the bicubic interpolation, allows the selection of the best tiles in the input image that can be super-resolved using bicubic interpolation, while the remaining tiles are processed using a DNN-based SR method. This approach allows us to consistently speed up the SR inference latency with only minimal degradation in image quality.p Extensive evaluation results with different SR baselines and datasets show how our EHT-SR approach can speed up inference by up to 20% and 39% on GPU and CPU platforms, respectively, without negatively impacting the quality of the super-resolved content
Sponsor
Date
Extent
Resource Type
Text
Resource Subtype
Undergraduate Research Option Thesis