Joint Sub-bands Learning with Clique Structures for Wavelet Domain Super-Resolution
arXiv:1809.04508
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.
arXiv commentAccepted in NIPS 2018
Cited by in corpus (7)
- Intriguing Findings of Frequency Selection for Image Deblurring
- DuDoNet: Dual Domain Network for CT Metal Artifact Reduction
- Wavelet Domain Style Transfer for an Effective Perception-distortion Tradeoff in Single Image Super-Resolution
- Online non-convex optimization with imperfect feedback
- NTIRE 2020 Challenge on Image Demoireing: Methods and Results
- Learning Non-linear Wavelet Transformation via Normalizing Flow
- Feedback Pyramid Attention Networks for Single Image Super-Resolution