High Resolution Demoire Network

Yang, Shanghui; Lei, Yajing; Xiong, Shuangyu; Wang, Wei

doi:10.1109/icip40778.2020.9191255

Cited by 16 publications

(23 citation statements)

References 10 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%

“…Yang et al [21] presented a new high-resolution demoire network to fully utilize relations among feature mappings of different resolutions and multi-scale information exchange to better separate and remove moire patterns, but it achieves limited success when a moiré pattern exhibits very severe large-scale coloured bands. Zheng et al [22] divided image demoireing into two subquestions, namely, moire pattern removal and color restoration, and restored moire patterns by using a learnable bandpass filter and tone mapping.…”

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

“…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