Dual-domain Deep Convolutional Neural Networks for Image Demoireing

Vien, An Gia; Park, Hyunkook; Lee, Chul

doi:10.1109/cvprw50498.2020.00243

Cited by 18 publications

(11 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Digital filtering could explore low-rank and sparsity constraint [3,4,5], but they fail when dealing with complex moiré patterns. Thus, many studies investigated bringing deep learning models to solve this complicated problem, extracting features of moiré in spatial domain [6,7], frequency domain [8,9], and dual domains [10]. Some models perform very well on the training and testing data, while they all have problems of robustness that requiring retrain when applying them on other cameras or displays, which is data and time costly.…”

Section: Key Requirements and Challengesmentioning

confidence: 99%

22‐3: An Adaptive Frequency Domain Demoiré Method for Display Test Images

Tang,

Luo,

2023

Symp Digest of Tech Papers

View full text Add to dashboard Cite

show abstract

Section: Key Requirements and Challengesmentioning

confidence: 99%

22‐3: An Adaptive Frequency Domain Demoiré Method for Display Test Images

Tang,

Luo,

2023

Symp Digest of Tech Papers

View full text Add to dashboard Cite

show abstract

“…Guo et al [11] introduced a dual-domain representation network working in both the discrete cosine transform (DCT) and pixel domains for reduction of compression artifacts, where the DCT and inverse DCT (IDCT) are used to construct a sub-network to learn the DCT-domain prior knowledge of JPEG compression. Gia Vien et al [37] tested a similar idea for moire artifact removal. Zheng et al [35] introduced an implicit DCT to extend the DCT-domain learning to color image compression artifact reduction.…”

Section: Related Workmentioning

confidence: 99%

Learning Frequency Domain Priors for Image Demoireing

Zheng

Yuan

Yan

et al. 2022

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Image demoireing is a multi-faceted image restoration task involving both moire pattern removal and color restoration. In this paper, we raise a general degradation model to describe an image contaminated by moire patterns, and propose a novel multi-scale bandpass convolutional neural network (MBCNN) for single image demoireing. For moire pattern removal, we propose a multi-block-size learnable bandpass filters (M-LBFs), based on a block-wise frequency domain transform, to learn the frequency domain priors of moire patterns. We also introduce a new loss function named Dilated Advanced Sobel loss (D-ASL) to better sense the frequency information. 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. To determine the most appropriate frequency domain transform, we investigate several transforms including DCT, DFT, DWT, learnable non-linear transform and learnable orthogonal transform. We finally adopt the DCT. Our basic model won the AIM2019 demoireing challenge. Experimental results on three public datasets show that our method outperforms state-of-the-art methods by a large margin.

show abstract

“…Zheng et al [1] addressed the diversity of moiré artifacts by developing learnable bandpass filters. In [6], [18], [19], [34], both the spatial domain and discrete cosine transform domain were used to exploit the complementary characteristics of moiré artifacts. Note that all the aforementioned CNN-based demoiréing algorithms require a large amount of aligned training pairs, and their performances rely heavily on the characteristics of the pairs.…”

Section: B Learning-based Image Demoiréingmentioning

confidence: 99%

“…For example, Zheng et al [1] developed learnable multi-scale bandpass filters to deal with the diversity of moiré artifacts in the frequency domain. Further, in [6], [18], [19], different characteristics of moiré artifacts in both spatial and frequency domains were exploited. However, the aforementioned approaches are based on supervised learning, which requires large amounts of clean and moiré image pairs for training.…”

Section: Introductionmentioning

confidence: 99%

Unpaired Screen-Shot Image Demoiréing With Cyclic Moiré Learning

et al. 2022

Self Cite

View full text Add to dashboard Cite

We propose an end-to-end unpaired learning approach to screen-shot image demoiréing based on cyclic moiré learning. The proposed cyclic moiré learning algorithm consists of the moiréing network and the demoiréing network. The moiréing network generates moiré images to construct a pseudo-paired set of moiré and clean images. Then, the demoiréing network is trained in a supervised manner using the generated pseudo-paired dataset to remove moiré artifacts. In the moiréing network, the moiré generation is separately learned as global pixel intensity degradation and moiré pattern generation for more realistic moiré artifact generation. Furthermore, the moiréing network and the demoiréing network are integrated together to be trained in an end-to-end manner. Experimental results on different datasets demonstrate that the proposed algorithm significantly outperforms state-of-the-art unsupervised demoiréing algorithms as well as image restoration algorithms.

show abstract

Dual-domain Deep Convolutional Neural Networks for Image Demoireing

Cited by 18 publications

References 31 publications

22‐3: An Adaptive Frequency Domain Demoiré Method for Display Test Images

22‐3: An Adaptive Frequency Domain Demoiré Method for Display Test Images

Learning Frequency Domain Priors for Image Demoireing

Unpaired Screen-Shot Image Demoiréing With Cyclic Moiré Learning

Contact Info

Product

Resources

About