RefQSR: Reference-based Quantization for Image Super-Resolution Networks
This work addresses the problem of deploying high-performance SISR models in resource-constrained environments, representing an incremental improvement in network quantization by exploiting image self-similarity.
The paper tackles the computational inefficiency of deep learning-based single image super-resolution (SISR) models by introducing RefQSR, a reference-based quantization method that uses high-bit quantization on representative patches to guide low-bit quantization of others, achieving effective results across various SISR networks and quantization methods.
Single image super-resolution (SISR) aims to reconstruct a high-resolution image from its low-resolution observation. Recent deep learning-based SISR models show high performance at the expense of increased computational costs, limiting their use in resource-constrained environments. As a promising solution for computationally efficient network design, network quantization has been extensively studied. However, existing quantization methods developed for SISR have yet to effectively exploit image self-similarity, which is a new direction for exploration in this study. We introduce a novel method called reference-based quantization for image super-resolution (RefQSR) that applies high-bit quantization to several representative patches and uses them as references for low-bit quantization of the rest of the patches in an image. To this end, we design dedicated patch clustering and reference-based quantization modules and integrate them into existing SISR network quantization methods. The experimental results demonstrate the effectiveness of RefQSR on various SISR networks and quantization methods.