Hybrid Pixel-Unshuffled Network for Lightweight Image Super-resolution

Authors

  • Bin Sun Northeastern University AInnovation Labs Inc.
  • Yulun Zhang ETH Zurich
  • Songyao Jiang Northeastern University
  • Yun Fu Northeastern University AInnovation Labs Inc.

DOI:

https://doi.org/10.1609/aaai.v37i2.25333

Keywords:

CV: Low Level & Physics-Based Vision

Abstract

Convolutional neural network (CNN) has achieved great success on image super-resolution (SR). However, most deep CNN-based SR models take massive computations to obtain high performance. Downsampling features for multi-resolution fusion is an efficient and effective way to improve the performance of visual recognition. Still, it is counter-intuitive in the SR task, which needs to project a low-resolution input to high-resolution. In this paper, we propose a novel Hybrid Pixel-Unshuffled Network (HPUN) by introducing an efficient and effective downsampling module into the SR task. The network contains pixel-unshuffled downsampling and Self-Residual Depthwise Separable Convolutions. Specifically, we utilize pixel-unshuffle operation to downsample the input features and use grouped convolution to reduce the channels. Besides, we enhance the depthwise convolution's performance by adding the input feature to its output. The comparison findings demonstrate that, with fewer parameters and computational costs, our HPUN achieves and surpasses the state-of-the-art performance on SISR. All results are provided in the github https://github.com/Sun1992/HPUN.

Downloads

Published

2023-06-26

How to Cite

Sun, B., Zhang, Y., Jiang, S., & Fu, Y. (2023). Hybrid Pixel-Unshuffled Network for Lightweight Image Super-resolution. Proceedings of the AAAI Conference on Artificial Intelligence, 37(2), 2375-2383. https://doi.org/10.1609/aaai.v37i2.25333

Issue

Section

AAAI Technical Track on Computer Vision II