# Image Super-Resolution Reconstruction Network Based on Structural Reparameterization and Feature Reuse

## TL;DR

This paper introduces a new image super-resolution network that uses feature reuse and structural reparameterization to reduce memory and computation needs while maintaining high performance.

## Contribution

The novel use of structural reparameterization and feature reuse in image super-resolution networks to achieve high efficiency and performance.

## Key findings

- The proposed network reduces algorithm parameters by 84.5% compared to performance-oriented networks like DRCT.
- Inference time is shortened by 49.8%, making it suitable for resource-constrained devices.
- The method improves the mean structural similarity index by 3.24% over lightweight algorithms.

## Abstract

In the task of integrated circuit micrograph acquisition, image super-resolution reconstruction technology can significantly enhance acquisition efficiency. With the advancement of deep learning techniques, the performance of image super-resolution reconstruction networks has improved markedly, but their demand for inference device memory has also increased substantially, greatly limiting their practical application in engineering and deployment on resource-constrained devices. Against this backdrop, we designed image super-resolution reconstruction networks based on feature reuse and structural reparameterization techniques, ensuring that the networks maintain reconstruction performance while being more suitable for deployment in resource-limited environments. Traditional image super-resolution reconstruction networks often redundantly compute similar features through standard convolution operations, leading to significant computational resource wastage. By employing low-cost operations, we replaced some redundant features with those generated from the inherent characteristics of the image and designed a reparameterization layer using structural reparameterization techniques. Building upon local feature fusion and local residual learning, we developed two efficient deep feature extraction modules, and forming the image super-resolution reconstruction networks. Compared to performance-oriented image super-resolution reconstruction networks (e.g., DRCT), our network reduces algorithm parameters by 84.5% and shortens inference time by 49.8%. In comparison with lightweight image reconstruction algorithms, our method improves the mean structural similarity index by 3.24%. Experimental results demonstrate that the image super-resolution reconstruction network based on feature reuse and structural reparameterization achieves an excellent balance between network performance and complexity.