Mop Moiré Patterns Using MopNet

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

doi:10.1109/iccv.2019.00251

Cited by 57 publications

(51 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare our method with three state-of-the-art demoireing methods [8], [20], [21] and moire patterns regarded as a special noise, two classical denoising methods [23], [37] are used for comparison.…”

Section: B Experimental Resultsmentioning

confidence: 99%

“…Table 1 is the quantitative results among DncNN [37], UNet [23], DMCNN [8], MopNet [20], and HRDN [21]. Functioning as a general image denoising method, DnCNN has limited effect for demoireing.…”

Section: B Experimental Resultsmentioning

confidence: 99%

“…They also proposed a nonlinear multiresolution (multiscale) convolutional neural network (MSCNN) to eliminate moiré artefacts within different frequency bands. He et al [20] proposed a network consisting of a multi-scale aggregated, edge-guided, and pattern attribute-aware network to further remove the moire pattern precisely, but they need the other two pretrained network to describe the appearance properties of moire patterns.…”

Section: A Methods For Image Demoireingmentioning

confidence: 99%

See 2 more Smart Citations

Efficient Attention Fusion Network in Wavelet Domain for Demoireing

et al. 2021

View full text Add to dashboard Cite

When taking pictures of electronic screens or objects with high-frequency textures, people often run across colorful rainbow patterns that are known as ''moire'', seriously affecting the image quality and subsequent processing. Current methods for removing moire patterns mostly extract multiscale information by downsampling pooling layers, which may inevitably cause information loss. To address this issue, this paper proposes a demoireing method in the wavelet domain. By employing both discrete wavelet transform (DWT) and inverse discrete wavelet transform (IDWT) instead of traditional downsampling and upsampling, this method can effectively increase the network receptive field without information loss. In addition, to further reconstruct more details of moire patterns, this paper proposes an efficient attention fusion module (EAFM). With a combination of efficient channel attention, spatial attention and local residual learning, this module 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. Extensive experiments based on public datasets have shown that this suggested method can efficiently remove moire patterns and has a good quantitative and qualitative performance.INDEX TERMS Demoire, deep learning, wavelet transform, attention mechanism.

show abstract

Section: B Experimental Resultsmentioning

confidence: 99%

Section: B Experimental Resultsmentioning

confidence: 99%

Section: A Methods For Image Demoireingmentioning

confidence: 99%

See 1 more Smart Citation

Efficient Attention Fusion Network in Wavelet Domain for Demoireing

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Because of the largely varying appearance of moire patterns, conventional image prior based [6], [10] algorithms are inadequate for the demoireing task. Only very recently, a few deep learning based attempts [13], [14], [15], [16], [17] have been made to address image demoireing. Recent work [14], [17], [18] tried to remove moire patterns of different frequency bands through multi-scale design.…”

Section: Introductionmentioning

confidence: 99%

“…Only very recently, a few deep learning based attempts [13], [14], [15], [16], [17] have been made to address image demoireing. Recent work [14], [17], [18] tried to remove moire patterns of different frequency bands through multi-scale design. DMCNN [14] proposed to deal with moire patterns with a multi-scale CNN with multi-resolution branches and summed up the outputs from different scales to obtain a final output.…”

Section: Introductionmentioning

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

FHDe2Net: Full High Definition Demoireing Network

Shi

Duan

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Mop Moiré Patterns Using MopNet

Cited by 57 publications

References 16 publications

Efficient Attention Fusion Network in Wavelet Domain for Demoireing

Efficient Attention Fusion Network in Wavelet Domain for Demoireing

Learning Frequency Domain Priors for Image Demoireing

FHDe2Net: Full High Definition Demoireing Network

Contact Info

Product

Resources

About