Image Demoireing with Learnable Bandpass Filters

  title={Image Demoireing with Learnable Bandpass Filters},
  author={Bolun Zheng and Shanxin Yuan and Gregory G. Slabaugh and Ale{\vs} Leonardis},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
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… 

Learning Frequency Domain Priors for Image Demoireing

This paper raises a general degradation model to describe an image contaminated by moire patterns, and proposes a novel multi-scale bandpass convolutional neural network (MBCNN) for single image demoireing.

Wavelet-Based Dual-Branch Network for Image Demoireing

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.

Self-Adaptively Learning to Demoire from Focused and Defocused Image Pairs

This paper proposes a self-adaptive learning method for demoireing a high-frequency image, with the help of an additional defocused moire-free blur image, and builds a new moire dataset, including images with screen and texture moire artifacts.

Image Demoiréing with a Dual-Domain Distilling Network

A dual-domain distilling network to remove moiré artifacts from a single camera-captured screen image in an end-to-end manner is proposed, and its superiority over state-of-the-art alternatives is revealed.

FPANet: Frequency-based Video Demoireing using Frame-level Post Alignment

A novel model called FPANet is proposed that learns to extract frame-invariant content features and outputting better quality temporally consistent images, outperforms the state-of-the-art approaches in terms of the image and video quality metrics.

Real-time Image Enhancer via Learnable Spatial-aware 3D Lookup Tables

A novel real-time image enhancer via learnable spatial-aware 3dimentional lookup tables(3D LUTs), which well considers global scenario and local spatial information, and that outperforms SOTA image enhancement methods on public datasets both subjectively and objectively.

Deep Learning for Screen-Shot Image Demoiréing: A Survey

A review and perspective on the recent advances in deep learning-based image demoiréing techniques and forelocks the problems to be solved in the coming years.

NTIRE 2020 Challenge on Image Demoireing: Methods and Results

This paper reviews the Challenge on Image Demoireing that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2020, and examines the current state-of-the-art in image and burst image demoireing problems.

SiamTrans: Zero-Shot Multi-Frame Image Restoration with Pre-Trained Siamese Transformers

A novel zero-shot multi-frame image restoration method for removing unwanted obstruction elements that vary in successive frames, constructed by Siamese transformers, encoders, and decoders called SiamTrans.

DomainPlus: Cross Transform Domain Learning towards High Dynamic Range Imaging

This paper proposes a cross-transform domain neural network for efficient HDR imaging, and proposes fronted Discrete Wavelet Transform and Discrete Cosine Transform-based learnable bandpass filters to formulate aCross- transform domain learning block, dubbed DomainPlus Block (DPB) for effective ghosting removal.



Deep joint demosaicking and denoising

A new data-driven approach forDemosaicking and denoising is introduced: a deep neural network is trained on a large corpus of images instead of using hand-tuned filters and this network and training procedure outperform state-of-the-art both on noisy and noise-free data.

Multi-Scale Dynamic Feature Encoding Network for Image Demoiréing

A multi-scale convolutional network to process images at different spatial resolutions, obtaining features in different frequency bands, and thus the method can jointly remove moire in different frequencies, can outperform the state of the arts in fidelity as well as perceptual on benchmarks.

Gated Fusion Network for Single Image Dehazing

An efficient algorithm to directly restore a clear image from a hazy input using an end-to-end trainable neural network that consists of an encoder and a decoder is proposed.

EDVR: Video Restoration With Enhanced Deformable Convolutional Networks

This work proposes a novel Video Restoration framework with Enhanced Deformable convolutions, termed EDVR, and proposes a Temporal and Spatial Attention (TSA) fusion module, in which attention is applied both temporally and spatially, so as to emphasize important features for subsequent restoration.

Implicit Dual-Domain Convolutional Network for Robust Color Image Compression Artifact Reduction

An implicit dual-domain convolutional network with a pixel position labeling map and quantization tables as inputs is proposed and is superior to the state-of-the-art methods and IDCN-f exhibits excellent abilities to handle a wide range of compression qualities with a little trade-off against performance.

Demoiréing of Camera-Captured Screen Images Using Deep Convolutional Neural Network

An approach of deep convolutional neural network for demoir\'s screen photos that can efficiently remove the moir\'e patterns for camera acquired screen images; the new technique outperforms the existing ones.

Perceptual Losses for Real-Time Style Transfer and Super-Resolution

This work considers image transformation problems, and proposes the use of perceptual loss functions for training feed-forward networks for image transformation tasks, and shows results on image style transfer, where aFeed-forward network is trained to solve the optimization problem proposed by Gatys et al. in real-time.

Deep bilateral learning for real-time image enhancement

This work introduces a new neural network architecture inspired by bilateral grid processing and local affine color transforms that processes high-resolution images on a smartphone in milliseconds, provides a real-time viewfinder at 1080p resolution, and matches the quality of state-of theart approximation techniques on a large class of image operators.

AIM 2019 Challenge on Image Demoireing: Methods and Results

This paper reviews the first-ever image demoireing challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ICCV 2019, and focuses on the proposed solutions and their results.

Accurate Image Super-Resolution Using Very Deep Convolutional Networks

This work presents a highly accurate single-image superresolution (SR) method using a very deep convolutional network inspired by VGG-net used for ImageNet classification and uses extremely high learning rates enabled by adjustable gradient clipping.