Wavelet-Based Dual-Branch Network for Image Demoireing
arXiv:2007.07173
Abstract
When smartphone cameras are used to take photos of digital screens, usually moire patterns result, severely degrading photo quality. In this paper, we design a wavelet-based dual-branch network (WDNet) with a spatial attention mechanism for image demoireing. Existing image restoration methods working in the RGB domain have difficulty in distinguishing moire patterns from true scene texture. Unlike these methods, our network removes moire patterns in the wavelet domain to separate the frequencies of moire patterns from the image content. The network combines dense convolution modules and dilated convolution modules supporting large receptive fields. Extensive experiments demonstrate the effectiveness of our method, and we further show that WDNet generalizes to removing moire artifacts on non-screen images. Although designed for image demoireing, WDNet has been applied to two other low-levelvision tasks, outperforming state-of-the-art image deraining and derain-drop methods on the Rain100h and Raindrop800 data sets, respectively.
Accepted to ECCV 2020
References in corpus (15)
- Adam: A Method for Stochastic Optimization
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- The Perception-Distortion Tradeoff
- Direction-aware Spatial Context Features for Shadow Detection and Removal
- Residual Dense Network for Image Super-Resolution
- MemNet: A Persistent Memory Network for Image Restoration
- Wavelet Convolutional Neural Networks for Texture Classification
- Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining
- Demoiréing of Camera-Captured Screen Images Using Deep Convolutional Neural Network
- Scaling the Scattering Transform: Deep Hybrid Networks
- Wavelet Integrated CNNs for Noise-Robust Image Classification
- Video Super-resolution with Temporal Group Attention
- A^2Net: Adjacent Aggregation Networks for Image Raindrop Removal
- Difficulty-aware Image Super Resolution via Deep Adaptive Dual-Network
- Image Demoireing with Learnable Bandpass Filters