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].”
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].”
BackgroundMop moiré patterns using mopnet
He, B., Wang, C., Shi, B., & Duan, L. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00251 · Cited by 97
“[20] proposed a multi-scale CNN to learn the mapping to moiré-free images, with a benchmark dataset captured on LCD screens of various models.”
BackgroundMethodInfluentialTowards efficient and scale-robust ultra-high-definition image demoiréing
Yu, X., Dai, P., Li, W., Ma, L., Shen, J., Li, J., & Qi, X. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-19797-0_37 · Cited by 93
Learning Frequency Domain Priors for Image Demoireing
Zheng, B., Yuan, S., Yan, C., Tian, X., Zhang, J., Sun, Y., Liu, L., Leonardis, A., & Slabaugh, G. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3115139 · Cited by 83
“Since some related work is evaluated on the TIP2018 dataset, we further evaluated our MBCNN on the TIP2018 dataset to compare with several related methods including DnCNN [69], VDSR [71], EDSR [63], UNet [39], DMCNN [14], MopNet [17], WDNet [13].”
BackgroundMethodInfluentialSelf-citationLearning-based image steganography and watermarking: A survey
Hu, K., Wang, M., Ma, X., Chen, J., Wang, X., & Wang, X. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.123715 · Cited by 108
Universal screen-shooting robust image watermarking with channel-attention in DCT domain
Cao, F., Guo, D., Wang, T., Yao, H., Li, J., & Qin, C. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122062 · Cited by 64
FHDe2Net: Full High Definition Demoireing Network
He, B., Wang, C., Shi, B., & Duan, L.-Y. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58542-6_43 · Cited by 62
Multi-scale dynamic feature encoding network for image demoiréing
Cheng, X., Fu, Z., & Yang, J. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00432 · Cited by 50
“proposed a demoiréing network based on multi-scale convolutional neural networks [15] and a large moiré image dataset based on ImageNet [3].”
BackgroundMethodInfluentialHuang, A. C., Meng, S. H., & Huang, T. J. (2023) · Cluster Computing · doi:10.1007/s10586-023-04115-6 · Cited by 58
Recaptured screen image demoiréing
Yue, H., Mao, Y., Liang, L., Xu, H., Hou, C., & Yang, J. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.2969984 · Cited by 42
“Sun et al. introduced a novel multi-resolution fully convolutional network to remove moiré patterns (DMCNN) [8].”
BackgroundMethodInfluentialAIM 2019 Challenge on Image Demoireing: Methods and Results
Yuan, S., Timofte, R., Slabaugh, G., Leonardis, A., Zheng, B., Ye, X., Tian, X., Chen, Y., Cheng, X., Fu, Z., et al. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00438 · Cited by 40
“Given the increasing occurrence of moire images resulting from digital photography of screens, coupled with the comparatively less attention the demoireing problem has received in the the community [13, 19], this demoireing challenge was proposed to fill this gap.”
BackgroundAIM 2019 Challenge on Image Demoireing: Dataset and Study
Yuan, S., Timofte, R., Slabaugh, G., & Leonardis, A. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00437 · Cited by 49
“Unlike the dataset in [11], LCDMoire does not suffer from alignment issues.”
BackgroundInfluentialDoing More With Moiré Pattern Detection in Digital Photos
Yang, C., Yang, Z., Ke, Y., Chen, T., Grzegorzek, M., & See, J. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3232232 · Cited by 42
“3) Restoration: In addition to FHDMi [43] and MRBI [68], the actively used dataset DMCNN [2] is also employed for the comparison of moiré image restoration before and after the employment of our framework.”
BackgroundMethodResultInfluentialFast and Lightweight Network for Single Frame Structured Illumination Microscopy Super-Resolution
Cheng, X., Li, J., Qiang, D., Fu, Z., & Yang, J. J. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3161721 · Cited by 30
Progressive Moire Removal and Texture Complementation for Image Demoireing
Niu, Y., Lin, Z., Liu, W., & Guo, W. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3237810 · Cited by 37
“Prior works [9], [13] simply employ element-wise feature aggregation to fuse the information of different scales, which does not fully utilize their correlations.”
BackgroundMethodInfluentialCoarse-to-fine Disentangling Demoiréing Framework for Recaptured Screen Images
Wang, C., He, B., Wu, S., Wan, R., Shi, B., & Duan, L.-Y. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3243310 · Cited by 29
“We follow this setup to make a fair comparison among all methods and reduce the time cost of training model considering the relatively large data scale of TIP-2018 [22].”
BackgroundMethodInfluentialMoiré Pattern Removal with Multi-scale Feature Enhancing Network
Gao, T., Guo, Y., Zheng, X., Wang, Q., & Luo, X. (2019) · IEEE International Conference on Multimedia & Expo Workshops (ICMEW) · doi:10.1109/icmew.2019.00048 · Cited by 43
“[14] tackled with moiré patterns from both high and low frequency bands, and proposed a multi-resolution fully convolutional neural network.”
BackgroundUnsupervised moiré pattern removal for recaptured screen images
Yue, H., Cheng, Y., Liu, F., & Yang, J. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.05.099 · Cited by 33
Recaptured screen image demoiréing in raw domain
Yue, H., Cheng, Y., Mao, Y., Cao, C., & Yang, J. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3198333 · Cited by 26
“We first compare with state-of-the-art image demoriéing methods, including DMCNN [4], MopNet [22], AMNet [6], FHDe 2 Net [5], C3Net [26], WDNet [23], MDDM [25], AFN [27], and the GAN-based image denoising method WGAN-VGG [56].”
BackgroundMethodInfluentialScreen-shooting resistant image watermarking based on lightweight neural network in frequency domain
Cao, F., Wang, T., Guo, D., Li, J., & Qin, C. (2023) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2023.103837 · Cited by 26
Dual-domain Deep Convolutional Neural Networks for Image Demoireing
Vien, A. G., Park, H., & Lee, C. (2020) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00243 · Cited by 31
“[28] exploited intrinsic correlations between moiré patterns and image components at different levels in a multi-resolution pyramid network.”
BackgroundMethodDeep wavelet network with domain adaptation for single image demoiréing
Luo, X., Zhang, J., Hong, M., Qu, Y., Xie, Y., & Li, C. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00218 · Cited by 24
“[13] first introduced the demoireing problem on camera images and proposed that the moire characteristics of camera images are muti-frequency.”
BackgroundHigh Resolution Demoire Network
Yang, S., Lei, Y., Xiong, S., & Wang, W. (2020) · Proceedings - International Conference on Image Processing · doi:10.1109/icip40778.2020.9191255 · Cited by 25
“Qualitative analysis of DnCNN [15], U-net [8], Sun [4], MopNet [1] and HRDN.”
MethodInfluentialSelf-citationImproved multi-scale dynamic feature encoding network for image demoiréing
Cheng, X., Fu, Z., & Yang, J. J. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.107970 · Cited by 24
P-BiC: Ultra-High-Definition Image Moiré Patterns Removal via Patch Bilateral Compensation
Xiao, Z., Lu, Z., & Wang, X. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681144 · Cited by 37
“Weconduct experimentsonfourpublicimagedemoiréing datasets: TIP2018 [25], LCDMoiré [46], FHDMi [7], and UHDM [45].”
InfluentialRecaptured screen image identification based on vision transformer
Li, G., Yao, H., Le, Y., & Qin, C. (2022) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2022.103692 · Cited by 21
Automatic image-domain Moiré artifact reduction method in grating-based x-ray interferometry imaging
Chen, J., Zhu, J., Li, Z., Shi, W., Zhang, Q., Hu, Z., Zheng, H., Liang, D., & Ge, Y. (2019) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ab3c34 · Cited by 22
MMDM: Multi-frame and Multi-scale for Image Demoiréing
Liu, S., Li, C., Nan, N., Zong, Z., & Song, R. (2020) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00225 · Cited by 31
Multiscale Coarse-to-Fine Guided Screenshot Demoiréing
Nguyen, D. H., Lee, S.-H., & Lee, C. (2023) · IEEE Signal Processing Letters · doi:10.1109/lsp.2023.3296039 · Cited by 21
“First, moiré patterns are unevenly distributed over an image and vary in shape, color, and frequency [1].”
BackgroundMethodMoiré pattern removal via attentive fractal network
Xu, D., Chu, Y., & Sun, Q. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00244 · Cited by 19
“In [30], a multi-scale convolution network is proposed to learn the mapping from moiré pat-”
BackgroundMethodResultInfluentialBai, R., Li, L., Zhang, S., Lu, J., & Chang, C. (2022) · Applied Sciences · doi:10.3390/app12199780 · Cited by 17
EigenGAN: An SVD subspace-based learning for image generation using Conditional GAN
Kas, M., Chahi, A., Kajo, I., & Ruichek, Y. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.111691 · Cited by 20
MoiréTag: Angular Measurement and Tracking with a Passive Marker
Qiu, S., Amata, H., & Heidrich, W. (2023) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3588432.3591538 · Cited by 22
“Another Moiré implementation is to minimize the Moiré fringes to improve the quality of a recaptured image from the display monitor [He et al. 2020; Sun et al. 2018; Yu et al. 2022].”
BackgroundAnti-Screenshot Watermarking Algorithm for Archival Image Based on Deep Learning Model
Wei, G., Chang, C., Bai, Y. S., Fan, Y., Tao, L., & Li, L. (2023) · Entropy · doi:10.3390/e25020288 · Cited by 15
Removing moiré patterns from single images
Fang, F., Wang, T., Wu, S., & Zhang, G. (2019) · Information Sciences · doi:10.1016/j.ins.2019.12.001 · Cited by 14
Image demoiréing in raw and srgb domains
Xu, S., Song, B., Chen, X., Liu, X., & Zhou, J. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-72658-3_7 · Cited by 14
Efficient Attention Fusion Network in Wavelet Domain for Demoireing
Sun, C., Lai, H., Wang, L., & Jia, Z. (2021) · IEEE Access · doi:10.1109/access.2021.3070809 · Cited by 15
“Sun et al. [8] created a large-scale benchmark dataset TIP dataset, which founded on ImageNet [9], plays a very important role in develop demoire methods.”
BackgroundMethodInfluentialScreen-shot and Demoiréd image identification based on DenseNet and DeepViT
Yao, H., Liu, T., Li, G., & Qin, C. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122580 · Cited by 15
Multi-scale Multi-attention Network for Moiré Document Image Binarization
Guo, Y., Ji, C., Zheng, X., Wang, Q., & Luo, X. (2020) · Signal Processing Image Communication · doi:10.1016/j.image.2020.116046 · Cited by 14
Std-net: spatio-temporal decomposition network for video demoiréing with sparse transformers
Niu, Y., Xu, R., Lin, Z., & Liu, W. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3386604 · Cited by 12
“3) Computational Efficiency Comparision: In Table III, we present the running time, parameters, and memory cost of our transformer-based model, as well as state-of-the-art CNN-based models, including DMCNN [3], MBCNN [12], ESDNet-L [14], and RBTC [6].”
BackgroundMethodInfluentialImage Hiding and Restoration via Deep Moiré Networks
Cheng, X., & Fu, Z. (2024) · IEEE Signal Processing Letters · doi:10.1109/lsp.2024.3383949 · Cited by 11
“We contrast our GRN against VDSR [29], DnCNN [30], DMCNN [23], MSFE [31], and MDDM [32] under stripe, ring, and grid degradations across three rows.”
BackgroundMethodInfluentialAdaptive Multispectral Encoding Network for Image Demoiréing
Dai, Q. G., Cheng, X., Zhang, L., & Sun, L.-K. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3280518 · Cited by 13
“We compare the performance of our proposed AMSDM method with several recent demoiréing approaches, including multi-scale bandpass CNN (MBCNN) [53], DMCNN [7], multi-scale feature enhancing (MSFE) network [9], MopNet [10], MDDM [8], and MDDM + [1].”
BackgroundMethodInfluentialLu, H.-P., Su, C., Yang, S.-Y., & Lin, Y.-P. (2020) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2020.3005164 · Cited by 11
“[20] proposed a multi-scale deep convolutional neural network (DCNN) for mapping moiré-free images.”
BackgroundLiu, L., Gao, Y., Chen, J., Zvomuya, F., & He, H. (2024) · Earth Surface Processes and Landforms · doi:10.1002/esp.5752 · Cited by 10
“It is also noteworthy that old photographs tend to underestimate satellite imagery-derived NDVI (Ardizzone, Dindo, & Mazzola, 2018; Sun, Yu, & Wang, 2018) whereas more recent photographs provide a better approximation, which may reflect the lower resolution of earlier cameras.”
BackgroundInverse Halftoning Methods Based on Deep Learning and Their Evaluation Metrics: A Review
Li, M., Zhang, E., Wang, Y., Duan, J., & Jing, C. (2020) · Applied Sciences · doi:10.3390/app10041521 · Cited by 11
Image Demoiréing via Multiscale Fusion Networks With Moiré Data Augmentation
Peng, Y., Hou, C.-H., Lee, Y.-C., Yoon, A. J., Chen, Z., Lin, Y.-T., & Lien, W.-C. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3392781 · Cited by 13
“All the experiments were completed on We compared the DMSFN with one conventional and nine deep-learning-based demoiréing methods, including RTV [13], DMCNN [14], HRDN [15], MopNet [22], WDNet [16], FHDe 2 Net [17], MBCNN [31], Uformer-B [5], ESDNet [27], and CDDF [33].”
BackgroundMethodInfluentialMUNet++: Multilevel wavelet nested UNet++ demoiréing residual network
Gao, G., Lai, H., & Jia, Z. (2024) · Displays · doi:10.1016/j.displa.2024.102741 · Cited by 10
Lightweight parameter de-redundancy demoiréing network with adaptive wavelet distillation
Chen, J., Mao, Q., Bao, Y., Huang, Y., Meng, F., & Liang, Y. (2023) · Journal of Real-Time Image Processing · doi:10.1007/s11554-023-01386-5 · Cited by 9
“Although DMCNN [4] employs the lowest parameters, the poor performance limits its usage of it in practical deployment.”
InfluentialVideo Demoiréing With Deep Temporal Color Embedding and Video-Image Invertible Consistency
Liu, L., An, J., Yuan, S., Zhou, W., Li, H., Wang, Y., & Tian, Q. C. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3366765 · Cited by 12
“Sun et al. [10] collect a large-scale image demoiréing dataset and design a multi-scale network.”
BackgroundMethodInfluentialFPANet: Frequency-based video demoiréing using frame-level post alignment
Oh, G., Kim, S., Gu, H., Yoon, S. H., Kim, J., & Kim, S. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.107021 · Cited by 16
“Table 1: Quantitative comparison with the state-of-the-art image (or video) demoiréing approaches: UNet [47], DMCNN [1], ESDNet [4], WDNet [5], MBCNN [3], and VDmoire [11].”
InfluentialC3net: demoiréing network attentive in channel, color, and concatenation
Kim, S., Nam, H., Kim, J., & Jeong, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00221 · Cited by 9
“[27] used CNN under conditions of diverse resolutions and added all and successfully removed moiré patterns in photographs.”
MethodUnpaired Screen-Shot Image Demoiréing With Cyclic Moiré Learning
Park, H., Vien, A. G., Kim, H., Koh, Y. J., & Lee, C. (2022) · IEEE Access · doi:10.1109/access.2022.3149478 · Cited by 11
“For example, in [2], [14]–[16], multiscale CNNs were employed for image demoiréing.”
BackgroundMethodInfluentialLearning Moiré Pattern Elimination in Both Frequency and Spatial Domains for Image Demoiréing
Liu, C., Wang, Y., Zhang, N., Gang, R., & Ma, S. (2022) · Sensors · doi:10.3390/s22218322 · Cited by 8
“Sun et al. [6] proposed a multi-resolution network (DMCNN) for the multi-frequency characteristics of moiré patterns.”
BackgroundPyramid Learnable Bandpass Filters for Ultra-High-Definition Image Demoiréing
Liu, Z., Zheng, B., Chen, Q., Zhang, Q., Jia, X., Zhang, J., & Yan, C. C. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3545898 · Cited by 13
“1) Demoiréing in the Spatial Domain: Sun et al. [33] pioneered the first learning-based approach, DMCNN, for the image demoiréing task and introduced the TIP2018 dataset, a benchmark for this domain.”
InfluentialMFGAN: towards a generic multi-kernel filter based adversarial generator for image restoration
Chahi, A., Kas, M., Kajo, I., & Ruichek, Y. (2023) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-023-01959-7 · Cited by 8
“TIP2018 [34] is the selected benchmark, which includes 135,000 image pairs, each consisting of an image damaged by moiré degradation and an uncor-rupted reference image.”
InfluentialSingle-Shot High Dynamic Range Imaging via Multiscale Convolutional Neural Network
Vien, A. G., & Lee, C. (2021) · IEEE Access · doi:10.1109/access.2021.3078457 · Cited by 8
“Multibranch networks have been shown to achieve better results than single networks in image enhancement [45], [46] and HDR imaging [28], [47].”
BackgroundWavelet-based enhancement network for low-light image
Hu, X., Liu, K., Yin, X., Gao, X., Jiang, P., & Qian, X. (2025) · Displays · doi:10.1016/j.displa.2024.102954 · Cited by 9
Eliminating Moiré Patterns Across Diverse Image Resolutions via DMMNet
Ma, Y., Qi, H., & Jin, Z. J. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3535324 · Cited by 7
“Images (a) are from TIP2018 [10] with the resolution of 384 × 384, image (b) is from FHDMI [12] with the resolution of 1920 × 1080, and image (c) is from UHDM [9] with the resolution of 3840 × 2160. strategies and pixel-wise constraints.”
InfluentialA Universal Scale-Adaptive Deformable Transformer for Image Restoration across Diverse Artifacts
He, X., Quan, Y., Xu, R., & Ji, H. (2025) · 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/cvpr52734.2025.01188 · Cited by 15
“[33] proposed a multi-resolution encoder-decoder architecture designed to model Moiré patterns at varying scales.”
InfluentialDocmarking: Real-Time Screen-Cam Robust Document Image Watermarking
Yakushev, A., Markin, Y. V., Obydenkov, D. O., Frolov, A. E., Fomin, S. A., Akopyan, M., Kozachok, A. V., & Gaynov, A. (2022) · Ivannikov ISPRAS Open Conference (ISPRAS) · doi:10.1109/ispras57371.2022.10076265 · Cited by 7
“At the moment, the problem of removing the moiré effect from photographs to improve their quality is actively studied [15], including screen photographs [16].”
BackgroundMultibranch Wavelet-Based Network for Image Demoiréing
Yeh, C.-H., Lo, C., & He, C.-H. (2024) · Sensors · doi:10.3390/s24092762 · Cited by 7
EEDNet: Enhanced Encoder-Decoder Network for AutoISP
Zhu, Y., Guo, Z., Liang, T., He, X., Li, C., Leng, C., Jiang, B., Zhang, Y., & Cheng, J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-67070-2_10 · Cited by 7
Kulkarni, V., Cung, N. Q., Bagley, A. M., Yang, N. T., Taylor, S. L., & Davids, J. R. (2023) · Developmental Medicine & Child Neurology · doi:10.1111/dmcn.15612 · Cited by 7
Linear Regression Supporting Vector Machine and Hybrid LOG Filter-Based Image Restoration
Basha, D. K., & Venkateswarlu, T. (2019) · Journal of Intelligent Systems · doi:10.1515/jisys-2018-0492 · Cited by 7
Beyond the Screen: Evaluating Deepfake Detectors under Moiré Pattern Effects
Tariq, R., Heo, M., Woo, S. S., & Tariq, S. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00446 · Cited by 14
Moiré pattern generation-based image steganography
Qin, T., Feng, B., Chen, B., Peng, Z., Xia, Z., & Lu, W. (2024) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2024.103753 · Cited by 6
Zhang, Y., Ni, J., Malwi, W. A., Asiri, F., Ahmad, J. E., & Jiang, D. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3547721 · Cited by 5
“To train the proposed ReSim, a subset of 11,000 image pairs are selected from the TIP2018 [29] dataset as the training set.”
Spatial Adaptive Filter Network With Scale-Sharing Convolution for Image Demoiréing
Xu, Y., Wei, Z., Xu, R., Zhou, Z., & Yu, Z. (2024) · IEEE Signal Processing Letters · doi:10.1109/lsp.2024.3451948 · Cited by 5
“Pioneering efforts can be traced back to Sun et al. [9], who introduced a multi-in-multi-out U-Shape architecture tailored for multi-scale processing.”
BackgroundLearning by competing: Competitive multi-generator based adversarial learning
Kajo, I., Kas, M., Chahi, A., & Ruichek, Y. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110698 · Cited by 7
Deep Multi-Scale Gabor Wavelet Network for Image Restoration
Dong, H., Zhang, X., Guo, Y., & Wang, F. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9053804 · Cited by 5
“Recent CNN-based approaches have taken an exploration of image demoiréing [3, 4].”
BackgroundImage Demoireing via U-Net for Detection of Display Defects
Kim, J.-H., Kong, K., & Kang, S. (2022) · IEEE Access · doi:10.1109/access.2022.3186685 · Cited by 6
“The existing demoireing networks have many parameters and are designed based on the existing moire datasets [13], [23].”
BackgroundMethodInfluentialEswindnet: Image Demoiréing Using Multiscale Swin Transformer Layers
Alaa, K., & Torki, M. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084615 · Cited by 4
Detection of Moiré pattern in high-resolution images
Zhang, Y., & Shen, L. (2023) · Signal Image and Video Processing · doi:10.1007/s11760-023-02781-y · Cited by 5
Deep Video Demoiréing via Compact Invertible Dyadic Decomposition
Quan, Y., Huang, H., He, S., & Xu, R. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01164 · Cited by 8
“However, typical DNNs like U-Net [6] and ResNet [22] used in these studies may result in incomplete information extraction for recovering all image details.”
BackgroundMethodInfluentialExtraction of patterns from images using a model of combined frequency localization spaces
Stanković, D., Ioana, C., & Orović, I. (2024) · Signal Processing · doi:10.1016/j.sigpro.2024.109810 · Cited by 4
Ensemble Model of Visual Transformer and CNN Helps BA Diagnosis for Doctors in Underdeveloped Areas
Wei, Z. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-27066-6_6 · Cited by 4
“Moiré patterns and other noise can catastrophically reduce the accuracy of the classification model, and CNN is proved to be effective in such denoising tasks as Moiré photo restoration [13, 14].”
MethodA Moiré Removal Method Based on Peak Filtering and Image Enhancement
Qi, W., Yu, X., Li, X., & Kang, S. (2024) · Mathematics · doi:10.3390/math12060846 · Cited by 6
Pervasive multifaceted process based generative adversarial network for image quality enhancement
Balaji, K. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113780 · Cited by 5
DSDNet: Raw Domain Demoiréing via Dual Color-Space Synergy
Yang, Q., Zhang, F., Jin, Y., Cheng, Q., Jiang, P.-T., Yue, H., & Yang, J. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3754698 · Cited by 13
“These methods have introduced innovative strategies such as frequency-domain modeling [6], multiscale feature fusion [19], and moiré pattern classification [10], leading to significant improvements in moiré removal.”
Espinosa-Bernal, O. A., Pedraza‐Ortega, J. C., Aceves-Fernández, M. A., Martínez-Suárez, V. M., & Tovar‐Arriaga, S. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-18082-8_2 · Cited by 3
A Contrastive Learning Approach for Screenshot Demoiréing
Nguyen, D. H., & Lee, C. (2023) · Proceedings - International Conference on Image Processing · doi:10.1109/icip49359.2023.10222647 · Cited by 5
Espinosa-Bernal, O. A., Pedraza‐Ortega, J. C., Aceves-Fernández, M. A., Martínez-Suárez, V. M., Tovar‐Arriaga, S., Ramos-Arreguín, J. M., & Gorrostieta-Hurtado, E. (2024) · Computers · doi:10.3390/computers13060145 · Cited by 3
“The deep learning network proposed in this article was based on the Multiresolution-CNN proposed by Sun [21] for periodic noise reduction in digital images, using as a comparison the same network used as the original Multiresolution-CNN base, the UNet network [22], and the FCN32s network [23],…”
BackgroundMethodInfluentialPluralistic Face Inpainting With Transformation of Attribute Information
Zhang, Y., Zhang, X., Shi, C., Wu, X., Li, X., Peng, J., Cao, K., Lv, J., & Zhou, J. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3229968 · Cited by 4
“[27]appliedatransformer[28] topluralisticimagecompletion(ICT),whichrecoverspluralis- ticcoherentstructuresandenhanceslocaltexturedetailsus-ingaconvolutionalneuralnetwork(CNN)[29].”
Method22‐3: An Adaptive Frequency Domain Demoiré Method for Display Test Images
Tang, H., Luo, X., & Xu, G. (2023) · SID Symposium Digest of Technical Papers · doi:10.1002/sdtp.16550 · Cited by 3
Super-Resolution of Color Halftone Images Using Convolutional Neural Networks
Novaes, G. A. S., & Kim, H. Y. (2024) · IEEE Access · doi:10.1109/access.2024.3352431 · Cited by 3
“In the literature, there are networks specifically designed to attenuate noise [27] and Moiré patterns [31] for continuous tone images.”
BackgroundMoiré Artifacts Removal in Screen-shot Images via Multiple Domain Learning
Vien, A. G., Park, H., & Lee, C. (2020) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · Cited by 3
The Effect of Bilateral Filtering in 3D Reconstruction Using PSP
Escoto, L. A. A., Pedraza‐Ortega, J. C., Arreguín, J. M. R., Hurtado, E. G., & Tovar‐Arriaga, S. (2020) · Communications in computer and information science · doi:10.1007/978-3-030-62554-2_20 · Cited by 3
Espinosa-Bernal, O. A., Pedraza‐Ortega, J. C., Aceves-Fernández, M. A., Ramos-Arreguín, J. M., Tovar‐Arriaga, S., & Gorrostieta-Hurtado, E. (2024) · Computers · doi:10.3390/computers13110290 · Cited by 2
Multi-spectral Dynamic Feature Encoding Network for Image Demoiréing
Dai, Q. G., Cheng, X., & Zhang, L. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-15937-4_13 · Cited by 3
Image inpainting via multi-resolution network with Fourier convolutions
Zhao, H., Shen, L., & Wang, J. (2024) · Signal Image and Video Processing · doi:10.1007/s11760-024-03111-6 · Cited by 2
P‐116: A Demoiré Method for Display Test Using CNN Model with Pixel Shift
Tang, H., Zhang, W., & Xu, G. (2024) · SID Symposium Digest of Technical Papers · doi:10.1002/sdtp.17940 · Cited by 2
FC3DNET: A Fully Connected Encoder-Decoder for Efficient Demoiréing
Du, Z., Peng, L., Wang, Y., Cao, Y., & Zha, Z.-J. (2024) · Proceedings - International Conference on Image Processing · doi:10.1109/icip51287.2024.10648032 · Cited by 16
Image blur analysis and elimination algorithm for an MTF test target of a space camera
Wang, C., Liu, C., Peng, J., Zhang, Y., Hu, H., & Liu, S. (2022) · Applied Optics · doi:10.1364/ao.441965 · Cited by 3
Deep Learning for Screen-Shot Image Demoiréing: A Survey
Hou, S., Wanga, Y.-B., Li, K., Zhao, Y., Lu, B., & Fan, L. (2022) · IEEE Access · doi:10.1109/access.2022.3213025 · Cited by 3
“In general, the methods of image demoiréing with deep learning differ in the following aspects: sampling methods [10], [14], [15], network design [14], [16], [17], baseline model [15], [16], [18], [21], [60], [61], and learning strategies [12], [18], [19], [20], [21], [22].”
BackgroundMethodInfluentialStudy on Waste Type Identification Method Based on Bird Flock Neural Network
Li, S., & Chen, L. (2020) · Mathematical Problems in Engineering · doi:10.1155/2020/9214350 · Cited by 2
Deep Learning-based Moiré Pattern Removal from a Single Image: A Survey and Comparative Study
Kang, L., Lo, C., & Yeh, C. (2020) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-taiwan49838.2020.9258241 · Cited by 2
“Based on [9], the performance of [25] would significantly drop for Moiré images taken with different capture settings from the training data.”
BackgroundMethodInfluential
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.