Image Demoireing with Learnable Bandpass Filters
arXiv:2004.00406
Abstract
Image demoireing is a multi-faceted image restoration task involving both texture and color restoration. In this paper, we propose a novel multiscale bandpass convolutional neural network (MBCNN) to address this problem. As an end-to-end solution, MBCNN respectively solves the two sub-problems. For texture restoration, we propose a learnable bandpass filter (LBF) to learn the frequency prior for moire texture removal. For color restoration, we propose a two-step tone mapping strategy, which first applies a global tone mapping to correct for a global color shift, and then performs local fine tuning of the color per pixel. Through an ablation study, we demonstrate the effectiveness of the different components of MBCNN. Experimental results on two public datasets show that our method outperforms state-of-the-art methods by a large margin (more than 2dB in terms of PSNR).
arXiv commentAccepted by CVPR2020. Code is available at https://github.com/zhenngbolun/Learnbale_Bandpass_Filter
References in corpus (10)
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- HDR image reconstruction from a single exposure using deep CNNs
- Image Super-Resolution Using Very Deep Residual Channel Attention Networks
- Residual Dense Network for Image Super-Resolution
- Learning Deep CNN Denoiser Prior for Image Restoration
- Implicit Dual-domain Convolutional Network for Robust Color Image Compression Artifact Reduction
- Densely Connected Pyramid Dehazing Network
- Gated Fusion Network for Single Image Dehazing
- Demoiréing of Camera-Captured Screen Images Using Deep Convolutional Neural Network
- Fast End-to-End Trainable Guided Filter