Joint Sub-bands Learning with Clique Structures for Wavelet Domain Super-Resolution

TL;DR

This paper introduces SRCliqueNet, a wavelet domain super-resolution method that uses clique structures to jointly learn wavelet coefficients, resulting in sharper images with better textural details than existing CNN-based approaches.

Contribution

The paper proposes a novel clique-based network architecture for wavelet domain super-resolution that jointly learns wavelet coefficients across sub-bands, improving detail reconstruction.

Findings

Outperforms state-of-the-art super-resolution methods on benchmark datasets.

Produces sharper images with richer textural details.

Demonstrates effectiveness of joint sub-band learning with clique structures.

Abstract

Convolutional neural networks (CNNs) have recently achieved great success in single-image super-resolution (SISR). However, these methods tend to produce over-smoothed outputs and miss some textural details. To solve these problems, we propose the Super-Resolution CliqueNet (SRCliqueNet) to reconstruct the high resolution (HR) image with better textural details in the wavelet domain. The proposed SRCliqueNet firstly extracts a set of feature maps from the low resolution (LR) image by the clique blocks group. Then we send the set of feature maps to the clique up-sampling module to reconstruct the HR image. The clique up-sampling module consists of four sub-nets which predict the high resolution wavelet coefficients of four sub-bands. Since we consider the edge feature properties of four sub-bands, the four sub-nets are connected to the others so that they can learn the coefficients of four sub-bands jointly. Finally we apply inverse discrete wavelet transform (IDWT) to the output of four sub-nets at the end of the clique up-sampling module to increase the resolution and reconstruct the HR image. Extensive quantitative and qualitative experiments on benchmark datasets show that our method achieves superior performance over the state-of-the-art methods.