Image Demoireing with Learnable Bandpass Filters

by   Bolun Zheng, et al.

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).


page 1

page 3

page 7

page 8


Global-Local Stepwise Generative Network for Ultra High-Resolution Image Restoration

While the research on image background restoration from regular size of ...

Learning Convolutional Sparse Coding on Complex Domain for Interferometric Phase Restoration

Interferometric phase restoration has been investigated for decades and ...

BoWFire: Detection of Fire in Still Images by Integrating Pixel Color and Texture Analysis

Emergency events involving fire are potentially harmful, demanding a fas...

GIF2Video: Color Dequantization and Temporal Interpolation of GIF images

Graphics Interchange Format (GIF) is a highly portable graphics format t...

Unfolding Taylor's Approximations for Image Restoration

Deep learning provides a new avenue for image restoration, which demands...

Invertible Tone Mapping with Selectable Styles

Although digital cameras can acquire high-dynamic range (HDR) images, th...

ROMNet: Renovate the Old Memories

Renovating the memories in old photos is an intriguing research topic in...

Code Repositories