Hybrid Pixel-Unshuffled Network for Lightweight Image Super-Resolution
This addresses the need for lightweight super-resolution models, making it more efficient for applications requiring high-quality image upscaling, though it appears incremental as it builds on existing downsampling and convolution techniques.
The paper tackles the problem of high computational costs in deep CNN-based image super-resolution models by proposing a Hybrid Pixel-Unshuffled Network (HPUN), which achieves state-of-the-art reconstruction performance with fewer parameters and computation costs.
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. Experiments on benchmark datasets show that our HPUN achieves and surpasses the state-of-the-art reconstruction performance with fewer parameters and computation costs.