Correction to: Fully 1 × 1 Convolutional Network for Lightweight Image Super-resolution

Gang Wu, Junjun Jiang, Kui Jiang, Xianming LiuMachine 2025 · DOI

TL;DR

This paper is a correction notice for a previously published article on lightweight image super-resolution using 1x1 convolutional networks. The correction clarifies that the original article was published without Open Access, but the authors have since opted for Open Choice, making it available under a Creative Commons license. The core technical contribution of the original paper (which this correction refers to) was the development of a novel 1x1 convolutional network architecture designed for efficient and effective image super-resolution.

What Problem Does This Paper Address?

The original paper (to which this is a correction) addresses the challenge of image super-resolution (SR), a task that aims to reconstruct a high-resolution (HR) image from a low-resolution (LR) counterpart. Traditional SR methods often involve computationally expensive models, making them unsuitable for resource-constrained environments like mobile devices or embedded systems. The authors sought to develop a lightweight yet effective SR model. Specifically, they focused on leveraging 1x1 convolutional layers, which are known for their efficiency in reducing dimensionality and increasing non-linearity without a significant increase in parameters, to build a super-resolution network.

Methods

This document is a correction notice and does not detail the methods of the original paper. However, it refers to a "Fully 1x1 Convolutional Network for Lightweight Image Super-resolution." This suggests the original work likely proposed a novel network architecture where 1x1 convolutions play a central role, potentially in feature extraction, dimensionality reduction, or channel-wise operations, to achieve efficient super-resolution. The "fully" aspect might imply an extensive use of 1x1 convolutions throughout the network.

Datasets

Not discussed in the paper.

Key Insights and Ideas

  • Open Access Transition: The primary insight from this document is the shift of the original article to an Open Access publication under a Creative Commons Attribution 4.0 International License. This makes the research more accessible to a wider audience.
  • Copyright Clarification: The copyright has been updated to reflect the Open Access status, attributing the work to "The Author(s) 2025."

Key Results

Not discussed in the paper.

Limitations and Future Work

Not discussed in the paper.

Summary updated

BibTeX
@inproceedings{wu2025correction,
  author = {Gang Wu and Junjun Jiang and Kui Jiang and Xianming Liu},
  title = {{Correction to: Fully 1 × 1 Convolutional Network for Lightweight Image Super-resolution}},
  booktitle = {Machine},
  year = {2025},
  doi = {10.1007/s11633-025-1549-1},
}
Figure