FHDe2Net: Full High Definition Demoireing Network

He, Bin; Shi, Boxin; Duan, Ling-Yu

doi:10.1007/978-3-030-58542-6_43

Cited by 26 publications

(36 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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%

Unpaired Screen-Shot Image Demoiréing With Cyclic Moiré Learning

et al. 2022

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

Section: B Learning-based Image Demoiréingmentioning

confidence: 99%

Unpaired Screen-Shot Image Demoiréing With Cyclic Moiré Learning

et al. 2022

View full text Add to dashboard Cite

show abstract

“…2, the difference between the moire and GT images is noticeable in the frequency domain. Given that MBCNN [18] and Full High Definition Demoireing Network (FHDe2Net) [7] perform DCT, Watermark-Decomposition Network (WDNet) [8] performs a wavelet transform, and Moire pattern Removal Neural Network (MopNet) [17] performs frequency analysis, several deep learning studies [7], [8], [17], [18] have tended to remove the moire pattern from the frequency domain. In contrast, we first applied the direct loss in the frequency domain.…”

Section: B) Frequency Lossmentioning

confidence: 99%

Image Demoireing via U-Net for Detection of Display Defects

2022

View full text Add to dashboard Cite

Mura defects, which occur during display manufacturing, degrade the quality of the display. Therefore, Mura detection is critical. When the camera is focused on the display for accurately detecting Mura defects, a moire pattern occurs in a captured image because of the frequency difference between the subpixels of the display and the color filter array of the camera. Typical image data handled with existing demoireing methods do not have Mura defects and include synthetic moire images. Therefore, we created a dataset to detect Mura defects that include real moire patterns, classified into two categories: weak and strong. We propose a new demoireing framework to remove the moire patterns in the captured image, thereby accurately detecting Mura defects. We also propose inserting ArUco markers for accurate alignment and automation, conducting multiple experiments with U-Net. Based on the captured data, the proposed U-Net, which combines a frequency loss and data augmentation, improves the performance by 6.41 dB higher for the weak moire pattern and 4.14dB higher for the strong moire pattern than state-of-the-art networks in terms of peak signal-to-noise ratio.

show abstract

“…Moiré patterns are mainly caused by the interference between the screen's subpixel layout and the camera's color filter array. Recently, some deep learning models (He et al 2020a;Zheng et al 2020;Yang et al 2020b;He et al 2019;Liu et al 2020a,b;Zheng et al 2021;Yuan et al 2019bYuan et al ,a, 2020 are proposed for single image demoiréing. For multi-frame demoiréing, Liu et al (Liu et al 2020c) use multiple images as inputs and design multi-scale feature encoding modules to enhance low-frequency information.…”

Section: Related Workmentioning

confidence: 99%

“…1) For multi-frame deraining, we compare with nine state-of-the-art methods, including three supervised single-image deraining methods (RES-CAN (Li et al 2018), MSPFN (Jiang et al 2020), and DID-MDN (Zhang and Patel 2018)), one unsupervised image restoration method (DGP (Pan et al 2020)), three unsupervised video deraining methods (MS-CSC (Li et al 2019), FastDerain (Jiang et al 2019), and SelfDerain (Yang et al 2020c)), and two supervised multi-frame image restoration methods (MLVR (Alayrac 2019) and LSTO (Liu et al 2020d)). 2) For multi-frame demoiréing, we compare with five state-of-the-art methods, including two supervised single-image demoiréing methods (MopNet (He et al 2019) and HRDN (Yang et al 2020b)) and three multi-frame demoiréing methods (MMDM (Liu et al 2020c), MLVR, and LSTO). 3) For multi-frame desnowing, we compare with one single-frame desnowing method (JSTASR (Chen et al 2020c)) and three video desnowing methods (MS-CSC, MLVR, and LSTO).…”

Section: Datasets and State-of-the-artsmentioning

confidence: 99%

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

Liu

Yuan

Liu

et al. 2022

AAAI

View full text Add to dashboard Cite

We propose a novel zero-shot multi-frame image restoration method for removing unwanted obstruction elements (such as rains, snow, and moire patterns) that vary in successive frames. It has three stages: transformer pre-training, zero-shot restoration, and hard patch refinement. Using the pre-trained transformers, our model is able to tell the motion difference between the true image information and the obstructing elements. For zero-shot image restoration, we design a novel model, termed SiamTrans, which is constructed by Siamese transformers, encoders, and decoders. Each transformer has a temporal attention layer and several self-attention layers, to capture both temporal and spatial information of multiple frames. Only self-supervisedly pre-trained on the denoising task, SiamTrans is tested on three different low-level vision tasks (deraining, demoireing, and desnowing). Compared with related methods, SiamTrans achieves the best performances, even outperforming those with supervised learning.

show abstract

FHDe2Net: Full High Definition Demoireing Network

Cited by 26 publications

References 34 publications

Unpaired Screen-Shot Image Demoiréing With Cyclic Moiré Learning

Unpaired Screen-Shot Image Demoiréing With Cyclic Moiré Learning

Image Demoireing via U-Net for Detection of Display Defects

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

Contact Info

Product

Resources

About