Moiré Photo Restoration Using Multiresolution Convolutional Neural Networks
Open accessThe DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
Abstract
Digital cameras and mobile phones enable us to conveniently record precious moments. While digital image quality is constantly being improved, taking high-quality photos of digital screens still remains challenging because the photos are often contaminated with moiré patterns, a result of the interference between the pixel grids of the camera sensor and the device screen. Moiré patterns can severely damage the visual quality of photos. However, few studies have aimed to solve this problem. In this paper, we introduce a novel multiresolution fully convolutional network for automatically removing moiré patterns from photos. Since a moiré pattern spans over a wide range of frequencies, our proposed network performs a nonlinear multiresolution analysis of the input image before computing how to cancel moiré artefacts within every frequency band. We also create a large-scale benchmark dataset with 100,000+ image pairs for investigating and evaluating moiré pattern removal algorithms. Our network achieves state-of-the-art performance on this dataset in comparison to existing learning architectures for image restoration problems.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Second, most existing demoir´ eing methods [7, 1, 13, 5, 16, 17, 18] struggle to remove large-scale, globally distributed moir´ e patterns in both images and videos.”
From MoCHA-former: Moiré-Conditioned Hybrid Adaptive Transformer for Video Demoiréing (2026) · cites this paper as [7]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“This phenomenon occurs due to factors such as the camera's perspective distortion, lens aberrations, and nonlinear distortions introduced by the ISP pipeline during the screen-capturing process [22, 1, 23].”
From MoCHA-former: Moiré-Conditioned Hybrid Adaptive Transformer for Video Demoiréing (2026) · cites this paper as [22]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“While recent methods adopt multi-scale architectures [7, 1, 8, 14] and symmetric encoder-decoder networks such as U-Net [24, 6, 2], they still fail to fully capture the global characteristics of moir´ e artifacts.”
From MoCHA-former: Moiré-Conditioned Hybrid Adaptive Transformer for Video Demoiréing (2026) · cites this paper as [7]
The cited source says what the claim attributes to it.
In the citing paper
“Fourth, image demoir´ eing models [7, 1, 13, 5] generally lack temporal modeling capabilities.”
From MoCHA-former: Moiré-Conditioned Hybrid Adaptive Transformer for Video Demoiréing (2026) · cites this paper as [7]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“00001 , and minimize the loss function using Adam [34].”
MethodImage quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892 · cited 1×
“As shown, our method and the variant of our model, V Concate, outperform all other methods participating in the comparison on all performance measures, including PSNR, SSIM [32] and FSIM [33].”
MethodGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
A Combined Corner and Edge Detector
Harris, C., & Stephens, M. (1988) · Procedings of the Alvey Vision Conference 1988 · doi:10.5244/c.2.23 · Cited by 12,901 · cited 1×
“Traditional corner detection methods, such as the Harris corner detector [30], can faithfully detect all corners in a target image (Fig.”
MethodBeyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
Zhang, K., Zuo, W., Chen, Y., Meng, D., & Zhang, L. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2662206 · Cited by 8,983 · cited 7×
“After successes in image classification and recognition [4], [5], they have also been proven highly effective in low-level vision and image processing tasks, including image super-resolution [6], [7], demosaicking [8], denoising [9], and restoration [10].”
BackgroundMethodResultInfluentialAccurate Image Super-Resolution Using Very Deep Convolutional Networks
Kim, J., Lee, J. K., & Lee, K. M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.182 · Cited by 7,870
Learning a Deep Convolutional Network for Image Super-Resolution
Dong, C., Loy, C. C., He, K., & Tang, X. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10593-2_13 · Cited by 5,494 · cited 2×
“Recently, learning techniques have been successfully applied to image restoration tasks, including image super-resolution [6], [7], [10], denoising [9], [10], and deblurring [10], [29].”
BackgroundFSIM: A Feature Similarity Index for Image Quality Assessment
Zhang, L., Zhang, L., Mou, X., & Zhang, D. (2011) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2109730 · Cited by 5,203 · cited 1×
“As shown, our method and the variant of our model, V Concate, outperform all other methods participating in the comparison on all performance measures, including PSNR, SSIM [32] and FSIM [33].”
MethodDeep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring
Nah, S., Kim, T. H., & Lee, K. M. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.35 · Cited by 2,275
Learning Deep CNN Denoiser Prior for Image Restoration
Zhang, K., Zuo, W., Gu, S., & Zhang, L. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.300 · Cited by 2,116 · cited 6×
“After successes in image classification and recognition [4], [5], they have also been proven highly effective in low-level vision and image processing tasks, including image super-resolution [6], [7], demosaicking [8], denoising [9], and restoration [10].”
BackgroundMethodInfluentialStructure extraction from texture via relative total variation
Xu, L., Yan, Q., Xia, Y., & Jia, J. (2012) · ACM Transactions on Graphics · doi:10.1145/2366145.2366158 · Cited by 867 · cited 6×
“RTV [2] and SDF [28] remove small-scale texture features which typically have higher frequencies than moir ´ e patterns.”
BackgroundMethodInfluentialDeep joint demosaicking and denoising
Gharbi, M., Chaurasia, G., Paris, S., & Durand, F. (2016) · ACM Transactions on Graphics · doi:10.1145/2980179.2982399 · Cited by 473 · cited 2×
“[8] presented a learning-based method to demosaic and denoise images.”
BackgroundMethodCho, H., Lee, H., Kang, H., & Lee, S. (2014) · ACM Transactions on Graphics · doi:10.1145/2601097.2601188 · Cited by 213 · cited 2×
“[3] combined the bilateral filter with a “patch shift” texture range kernel to achieve a similar goal.”
BackgroundStructure-preserving image smoothing via region covariances
Karacan, L., Erdem, E., & Erdem, A. (2013) · ACM Transactions on Graphics · doi:10.1145/2508363.2508403 · Cited by 212 · cited 1×
“Karacan et al. [25] took advantage of region covariances to separate texture from image structure.”
BackgroundRobust image filtering using joint static and dynamic guidance
Ham, B., Cho, M., & Ponce, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299115 · Cited by 147 · cited 6×
“Corrected Input RTV [2] SDF [28] IRCNN [10] DnCNN [9] VDSR [7] PyramidCNN [29] U-Net [31] V Concate Our method”
BackgroundMethodInfluentialCartoon-Texture Image Decomposition Using Blockwise Low-Rank Texture Characterization
Ono, S., Miyata, T., & Yamada, I. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2299067 · Cited by 139 · cited 1×
“Ono et al. [26] utilised block-wise low-rank texture characterisation to decompose images into texture and structure components.”
BackgroundInverse halftoning and kernel estimation for error diffusion
Wong, P. W. (1995) · IEEE Transactions on Image Processing · doi:10.1109/83.370677 · Cited by 121 · cited 1×
“Various methods have been proposed, such as printer-end algorithms [16], [17], image smoothing techniques [18], learning based methods [19], [20], and advanced filters [21]–[23].”
MethodAdaptive threshold modulation for error diffusion halftoning
Damera-Venkata, N., & Evans, B. L. (2001) · IEEE Transactions on Image Processing · doi:10.1109/83.892447 · Cited by 70
A robust technique for image descreening based on the wavelet transform
Luo, J., de Queiroz, R. L., & Fan, Z. (1998) · IEEE Transactions on Signal Processing · doi:10.1109/78.668572 · Cited by 60 · cited 1×
“Various methods have been proposed, such as printer-end algorithms [16], [17], image smoothing techniques [18], learning based methods [19], [20], and advanced filters [21]–[23].”
MethodMoiré pattern removal from texture images via low-rank and sparse matrix decomposition
Liu, F., Yang, J., & Yue, H. (2015) · 2015 Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip.2015.7457907 · Cited by 56 · cited 1×
“. Thus, their method is unsuitable for eliminating the moire patterns in our context. Observing that moir´ e´ patterns on textures are dissimilar while a texture is locally well-patterned, Liu et al. [14] proposed a low-rank and sparse matrix decomposition method to remove moir´e patterns on high-frequency textures. B…”
MethodSiddiqui, H., & Bouman, C. A. (2007) · IEEE Transactions on Image Processing · doi:10.1109/tip.2006.888356 · Cited by 47 · cited 1×
“Various methods have been proposed, such as printer-end algorithms [16], [17], image smoothing techniques [18], learning based methods [19], [20], and advanced filters [21]–[23].”
MethodScanned Image Descreening With Image Redundancy and Adaptive Filtering
Sun, B., Li, S., & Sun, J. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2332394 · Cited by 39 · cited 1×
“Various methods have been proposed, such as printer-end algorithms [16], [17], image smoothing techniques [18], learning based methods [19], [20], and advanced filters [21]–[23].”
MethodSuppression of moiré patterns via spectral analysis
Sidorov, D. N., & Kokaram, A. C. (2002) · SPIE Proceedings · doi:10.1117/12.453134 · Cited by 37
Automated removal of quasiperiodic noise using frequency domain statistics
Sur, F., & Grédiac, M. (2015) · Journal of Electronic Imaging · doi:10.1117/1.jei.24.1.013003 · Cited by 34 · cited 1×
“Taking advantage of frequency domain statistics, Sur and Gr ´ ediac [15] proposed to remove quasi-periodic noise.”
BackgroundSiddiqui, H., Boutin, M., & Bouman, C. A. (2010) · IEEE Transactions on Image Processing · doi:10.1109/tip.2009.2035238 · Cited by 33
AM/FM halftoning: digital halftoning through simultaneous modulation of dot size and dot density
He, Z., & Bouman, C. A. (2004) · Journal of Electronic Imaging · doi:10.1117/1.1669555 · Cited by 32 · cited 1×
“Various methods have been proposed, such as printer-end algorithms [16], [17], image smoothing techniques [18], learning based methods [19], [20], and advanced filters [21]–[23].”
MethodFast Patch-Based Denoising Using Approximated Patch Geodesic Paths
Chen, X., Kang, S. B., Yang, J., & Yu, J. (2013) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2013.160 · Cited by 27 · cited 1×
“Conventional image denoising [1], and texture removal techniques [2], [3] are not well suited for this problem because these techniques typically assume noises and textures occupy a higher-frequency band than true image structures.”
BackgroundImage Descreening by GA-CNN-Based Texture Classification
Shou, Y., & Lin, C. (2004) · IEEE Transactions on Circuits and Systems I Fundamental Theory and Applications · doi:10.1109/tcsi.2004.836861 · Cited by 22 · cited 3×
“Various methods have been proposed, such as printer-end algorithms [16], [17], image smoothing techniques [18], learning based methods [19], [20], and advanced filters [21]–[23].”
BackgroundMethodPaper check image quality enhancement with Moire reduction
Ok, J., Youn, S., Seo, G., Choi, E., Baek, Y., & Lee, C. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-4080-0 · Cited by 5 · cited 1×
“Specialised methods have been proposed to process a specific subset of images, such as paper checks [24].”
Method
Research works printed but not linked: 3
- 2017, Moiré Pattern
- 2017, Moiré
- sun, 0, Image structure retrieval via $L_{0}$ minimization, IEEE Trans Vis Comput Graphics
Cited by
Uformer: A General U-Shaped Transformer for Image Restoration
Wang, Z., Cun, X., Bao, J., Zhou, W., Liu, J., & Li, H. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01716 · Cited by 2,274
“A popular solution is to learn effective models using the U-shaped structures with skip-connection to capture multi-scale information hierarchically for various image restoration tasks, including image denoising [9, 74, 77], deblurring [3, 28, 29], and demoireing [38, 55].”
MethodWaveDM: Wavelet-Based Diffusion Models for Image Restoration
Huang, Y., Huang, J., Liu, J., Yan, M., Yu, D., Lv, J., Chen, C., & Chen, S. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3359769 · Cited by 204
Wavelet-Based Dual-Branch Network for Image Demoiréing
Liu, L., Liu, J., Yuan, S., Slabaugh, G., Leonardis, A., Zhou, W., & Tian, Q. C. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58601-0_6 · Cited by 186
Image Demoireing with Learnable Bandpass Filters
Zheng, B., Yuan, S., Slabaugh, G., & Leonardis, A. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00369 · Cited by 122
“We have conducted extensive ablation studies and out-performed state-of-the-art by large margins on two public datasets: LCDMoire [41] and TIP2018 [31] The LCDMoie dataset consists of 10,200 synthetically generated image pairs with 10,000 training images, 100 validation images and 100 testing…”
BackgroundMethodResultInfluentialReduce Information Loss in Transformers for Pluralistic Image Inpainting
Liu, Q., Tan, Z., Chen, D., Chu, Q., Dai, X., Chen, Y., Liu, M., Yuan, L., & Yu, N. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01106 · Cited by 154
“images, has always been a hot topic in computer vision areas and widely used in various applications [1, 35, 39, 42, 47, 48, 56].”
Background
Metadata
- Authors
- Sun, Y., Yu, Y., & Wang, W.
- Affiliations
- University of Hong Kong (HK)
- Venue
- IEEE Transactions on Image Processing
- Published
- 2018-08
- Volume
- 27
- Issue
- 8
- Pages
- 4160-4172
- ISSN
- 1057-7149 (ISSN-L)
- 1941-0042
- OpenAlex
- W2802445786
- Cited by
- 162
- References
- 28
- Citations by year
- 2026: 18 · 2025: 33 · 2024: 29 · 2023: 25 · 2022: 21 · 2021: 7 · 2020: 21 · 2019: 8
- FWCI
- 4.50
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Transactions on Image Processing (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Hong Kong Research Grants Council through General Research Funds (HKU17209714)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image Processing Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Enhancement Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Signal Denoising Methods
- Keywords
- image restoration, multiresolution analysis, fully convolutional network, frequency band filtering, benchmark dataset
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.