Image Demoireing with Learnable Bandpass Filters

@article{Zheng2020ImageDW,
  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)},
  year={2020},
  pages={3633-3642}
}
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… 
Wavelet-Based Dual-Branch Network for Image Demoireing
TLDR
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
TLDR
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.
Moiré Artifacts Removal in Screen-shot Images via Multiple Domain Learning
  • Vien Gia An, Hyunkook Park, Chul Lee
  • Computer Science
    2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
  • 2020
TLDR
This work develops the pixel and discrete cosine transform networks to estimate clean preliminary images by exploiting complementary information of the moiré artifacts in different domains and proposes the refinement network to further improve the quality of the pixels and DCT outputs.
Real-time Image Enhancer via Learnable Spatial-aware 3D Lookup Tables
  • Tao Wang, Yong Li, +4 authors Youliang Yan
  • Computer Science, Engineering
    ArXiv
  • 2021
TLDR
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 which outperforms SOTA image enhancement methods on public datasets both subjectively and objectively.
SiamTrans: Zero-Shot Multi-Frame Image Restoration with Pre-Trained Siamese Transformers
TLDR
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.
NTIRE 2020 Challenge on Image Demoireing: Methods and Results
TLDR
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.
MSR-Net: Multi-Scale Relighting Network for One-to-One Relighting
TLDR
This work proposes the use of Stacked Deep Multi-Scale Hierarchical Network, which aggregates features from each image at different scales, which is differentiable and robust for translating image illumination setting from input image to target image.
Hard parameter sharing for compressing dense-connection-based image restoration network
TLDR
The distribution of convolution layers is studied and a hard parameter sharing approach known as convolution pool (CP) is proposed for compressing dense-connection-based image restoration CNN models, which can efficiently achieve an impressive compression rate with negligible performance reduction.
CNN-based morphological decomposition of X-ray images for details and defects contrast enhancement
TLDR
A new learning based framework for X-ray images that relies on a morphological decomposition of the signal into two main components, separating images into local textures and piecewise smooth (cartoon) parts is introduced.
Efficient Attention Fusion Network in Wavelet Domain for Demoireing
TLDR
This paper proposes an efficient attention fusion module (EAFM), a combination of efficient channel attention, spatial attention and local residual learning that can self-adaptively learn various weights of feature information at different levels and inspire the network to focus more on effective information such as moire details to improve learning and demoireing performance.
...
1
2
...

References

SHOWING 1-10 OF 54 REFERENCES
Deep joint demosaicking and denoising
TLDR
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
TLDR
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.
Moiré Photo Restoration Using Multiresolution Convolutional Neural Networks
TLDR
A novel multiresolution fully convolutional network for automatically removing moiré patterns from photos, which achieves the state-of-the-art performance on this data set in comparison to existing learning architectures for image restoration problems.
Gated Fusion Network for Single Image Dehazing
TLDR
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
TLDR
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.
Multi-level Wavelet-CNN for Image Restoration
TLDR
This paper presents a novel multi-level wavelet CNN model for better tradeoff between receptive field size and computational efficiency, and shows the effectiveness of MWCNN for image denoising, single image super-resolution, and JPEG image artifacts removal.
Implicit Dual-Domain Convolutional Network for Robust Color Image Compression Artifact Reduction
TLDR
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
TLDR
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
TLDR
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
TLDR
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.
...
1
2
3
4
5
...