A Cost-Effective Interpolation for Multi-Magnification Super-Resolution

Abstract

Super-Resolution (SR) was an important research topic, and SR methods based on Convolutional Neural Network (CNN) confirmed its groundbreaking performance. However, notably implementing the CNN model into resource-limited hardware devices is a great challenge. Therefore, we present a hardware-friendly and low-cost interpolation for Multi-Magnification SR image reconstruction. We follow our previous work, which is a learning-based interpolation (LCDI) with a self-defined classifier of image texture, and extend its original $\times 2$ architecture to $\times 3$ and $\times 4$ architecture. Besides, the required pre-trained weights are reduced by the fusion scheme. Experimentally, the proposed method has only 75% lower pre-trained weights than LCDI. Compared to the related work OLM-SI (One linear learning mapping-SI), the run-time and quantity of pre-trained weights of the $\times 2$ proposed method are at least 90% lower. Compared to CNN-based SR methods, the proposed method loses a little lower performance, but the evaluation of computational cost is much lower. In conclusion, the proposed method is cost-effective and a practical solution for resource-limited hardware and device.

Keywords

• Super-resolution
• interpolation
• multi-magnification
• hardware-friendly
• machine learning