隨著科技發展，手機或相機已經成為每個人普遍都擁有的產品，也拜科技所賜，手機與相機的畫素也越來越高，在我們利用鏡頭去記錄美好的瞬間或是必要的資訊，當拍攝到特定條紋或是顯示螢幕，就會出現摩爾紋，摩爾紋的出現大大的破壞了影像的品質與紀錄的意義。近年來，因為深度學習技術的成熟，解決摩爾紋影像，不在侷限於傳統的方法。為了解決摩爾紋影像在不同頻率與不同尺度下的影響，在本研究中，提出以編碼器解碼器為基礎架構，來處理不同尺度下的摩爾紋影像，而為了使模型能夠更有效的取得摩爾紋的細節，我們利用小波轉換，將影像作用於小波域，使其能夠捕捉垂直與水平方向的高頻低頻細節，再透過雙通道注意力模組，捕捉影像的任意兩點的空間依賴性與通道依賴關係，從而增強模型的特徵表示。本研究將該模型實測在四個摩爾紋的公開資料集上都擁有不錯的表現。

With the development of technology, smartphones and cameras have become common devices that everyone has. Thanks to technological advancements, the resolution of these devices have also improved. When we use lenses to record essential information or to capture beautiful moments, we often encounter the moire pattern issue if photographing specific patterns or display screens. The moire pattern significantly degrades the image quality and lost the purpose of the recorded content. In recent year, the maturity of deep learning techniques, let image demoireing no longer use traditional method. In this study, we propose a framework based on an encoder-decoder architecture, combined with wavelet transforms to operate image on wavelet domain, this approach allows us to capture more moire pattern details. Additionally, a dual attention module is applied to enhance the feature representation of the model. We evaluate the performance of our method on four public moire pattern dataset and it is demonstrated that our method achieves better result compared with other state-of-the-art method.

[1] K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, “Beyond a gaussian denoiser : Residual learning of deep cnn for image denoising,” Transactions on Image Processing, pp. 3142-3155, jul, 2017
[2] B. Park, and J. Jeong, “Color Filter Array Demosaicking Using Densely Connected Residual Network,” Access, pp. 3142-3155, sep, 2019.
[3] F. Liu, J. Yang, and H. Yue, “Moiré pattern removal from texture images via low-rank and sparse matrix decomposition,” Visual Communications and Image Processing (VCIP), pp. 1-4, 2015.
[4] Y. Sun, Y. Yu, and W. Wang, “Moiré Photo Restoration Using Multiresolution Convolutional Neural Networks,” Transactions on Image Processing, pp. 4160-4172, aug, 2018
[5] B. He, C. Wang, B. Shi, LY. Duan, “FHDe2Net: Full High Definition Demoireing Network,” European Conference on Computer Vision (ECCV), 2020, pp. 713–729.
[6] X. Yu, “Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoiréing,” European Conference on Computer Vision (ECCV), 2022,
[7] K. Nishioka, N. Hasegawa, K. Ono, Y. Tatsuno, “Endoscope System Provided with Low-Pass Filter for Moire Removal,” U.S. Patent, 1997.
[8] D.N. Sidorov, A.C. Kokaram, “Suppression of moiré patterns via spectral analysis”, Visual Communications and Image Processing(VCIP), 2002, pp. 895-906.
[9] J. Yang, F. Liu, H. Yue, X. Fu, C. Hou, F. Wu, “Textured Image Demoiréing via Signal Decomposition and Guided Filtering,” Transactions on Image Processing, pp. 3528-3541, jul, 2017
[10] T. Gao, Y. Guo, X. Zheng, Q. Wang, and X. Luo, “Moiré Pattern Removal with Multi-scale Feature Enhancing Network,” International Conference on Multimedia & Expo Workshops (ICMEW), 2019, pp. 240-245.
[11] X. Cheng, Z. Fu, and J. Yang, “Multi-Scale Dynamic Feature Encoding Network for Image Demoiréing,” International Conference on Computer Vision Workshop (ICCVW), 2019, pp. 3486-3493
[12] B. He, C. Wang, B. Shi, and L. Duan, “Mop Moiré Patterns Using MopNet,” International Conference on Computer Vision (ICCV), 2019, pp. 2424-2432.
[13] B. Zheng, S. Yuan, G. Slabaugh and A. Leonardis, “Image Demoireing with Learnable Bandpass Filters,” Conference on Computer Vision and Pattern Recognition(CVPR), 2020, pp. 3633-3642
[14] K. He, X. Zhang, S. Ren, J. Sun, “Deep Residual Learning for Image Recognition,” Computer Vision and Pattern Recognition(CVPR), 2016, pp. 770-778.
[15] G. Huang, Z.Liu, L. Maaten, K. Q. Weinberger, “Densely Connected Convolutional Networks,” Computer Vision and Pattern Recognition(CVPR), 2017, pp. 4700-4708
[16] J. Kim, J. K. Lee, K. M. Lee, “Accurate Image Super-Resolution Using Very Deep Convolutional Networks,” Computer Vision and Pattern Recognition(CVPR), 2016, pp. 1646-1654.
[17] B. Lim, S. Son, H. Kim, S. Nah, K. M. Lee, “Enhanced Deep Residual Networks for Single Image Super-Resolution,” Computer Vision and Pattern Recognition(CVPR), 2017, pp. 136-144.
[18] R. Zhang, P. Isola, A. A. Efros, E. Shechtman, O. Wang, “The Unreasonable Effectiveness of Deep Features as a Perceptual Metric,” Computer Vision and Pattern Recognition(CVPR), 2018, pp. 586-595.
[19] S. W. Zamir, A. Arora, S. Khan, M. Hayat, F. S. Khan, M.-H. Yang, L. Shao, “Multi-Stage Progressive Image Restoration,” Computer Vision and Pattern Recognition(CVPR), 2021, pp. 14821-14831.
[20] S. Anwar, and N. Barnes, “Densely Residual Laplacian Super-Resolution,” Transactions on Pattern Analysis and Machine Intelligence, pp. 1192-1204, Mar. 2022.
[21] W. Shi, J. Caballero, F. Huszar, J. Totz, A. P. Aitken, R. Bishop, D. Rueckert, Z. Wang, “Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network,” Computer Vision and Pattern Recognition(CVPR), 2016, pp. 1874-1883.
[22] J. Johnson, A. Alahi, F.-F. Lee, “Perceptual Losses for Real-Time Style Transfer and Super-Resolution,” European Conference on Computer Vision (ECCV), 2016, pp. 694–711.
[23] S. Yuan, “AIM 2019 Challenge on Image Demoireing: Methods and Results,” International Conference on Computer Vision Workshop (ICCVW), 2019, pp. 3534-3545
[24] S. Yuan, R. Timofte, G. Slabaugh and A. Leonardis, “AIM 2019 Challenge on Image Demoireing: Dataset and Study,” International Conference on Computer Vision Workshop (ICCVW), 2019, pp. 3526-3533.
[25] C. Harris and M. Stephens, “A combined corner and edge detector,” Alvey vision conference, 1988, pp.10–5244.
[26] A. Vedaldi, B. Fulkerson, “Vlfeat: An open and portable library of computer vision algorithms,” ACM international conference on Multimedia, 2010, pp. 1469–1472.
[27] I. Loshchilov, F. Hutter, “Sgdr: Stochastic gradient descent with warm restarts,” arXiv preprint., 2016.
[28] L. Liu, J. Liu, S. Yuan, G. Slabaugh, A. Leonardis, W. Zhou, Q. Tian, “Waveletbased dual-branch network for image demoir´eing,” European Conference on Computer Vision (ECCV), 2020, pp. 86–102.