融合多尺度特征的高效去除图像摩尔纹算法
1. 四川师范大学, 计算机科学学院, 四川成都 610101
2. 四川师范大学, 物理与电子工程学院, 四川成都 610101
| 摘 要： | 针对图像摩尔纹干扰复杂多样、纹理细节与边缘信息难以被充分保留，以及现有去摩尔纹模型效果欠佳、计算复杂度较高等问题，本文提出了一种基于UNet的高效去摩尔纹算法MSFDNet（Multi-Scale Feature and Density-aware Network）。首先，在特征提取阶段引入基于密度参数的加权卷积层（WCL），通过自适应权重调整增强卷积核中心区域响应；其次，设计多尺度特征增强模块（MCFE），利用不同膨胀率卷积分支结合通道注意力机制，有效捕获跨尺度纹理特征；同时提出空间特征调制模块（SFM），通过空间注意力机制突出摩尔纹干扰集中区域，提升网络对空间分布差异的感知能力；在解码阶段结合跳跃连接与残差连接策略，实现多尺度信息的有效融合与鲁棒恢复。MSFDNet算法在TIP、FHDMi与UHDM三个公开数据集上，在PSNR、SSIM和LPIPS三项评估指标上均优于目前主流的去摩尔纹算法。在TIP数据集上，PSNR达到31.04 dB、SSIM达到0.943，较其他算法有明显提升；在FHDMi数据集上，PSNR达到24.695 dB，在UHDM数据集上SSIM提升至0.8154，均优于目前主流算法；所提算法能够在有效去除图像摩尔纹的同时保持图像纹理与边缘细节，兼具更强的泛化能力与鲁棒性。 |
| 关 键 词： | 图像摩尔纹去除; 加权卷积; 多尺度特征增强; Unet |
| DOI： | 10.57237/j.cst.2026.01.002 |
View:
Downloads:
收稿日期: 2025-12-11
接受日期: 2026-01-12
在线出版日期: 2026-01-20
Efficient Image Moir é Removal Algorithm That Integrates Multi-scale Features
1. College of Computer Science, Sichuan Normal University, Chengdu 610101, China
2. College of Physics and Electronic Engineering, Sichuan Normal University, Chengdu 610101, China
| Abstract: | Aiming at the complex and diverse interference of image moir é patterns, the difficulty in fully preserving texture details and edge information, and the poor performance and high computational complexity of existing moir é pattern removal models, a new moir é pattern removal network model based on UNet network is proposed, which integrates weighted convolution and multi-scale attention mechanism. In the feature extraction stage, a weighted convolutional layer based on density parameters is introduced to enhance the central region response of the convolutional kernel through adaptive weight adjustment, while suppressing the influence of edge noise. Secondly, in order to more effectively capture multi-scale feature information, spatial attention blocks and multi-scale channel attention modules are used for deep level feature extraction to obtain more detailed and rich feature representations. In the decoding stage, a combination of skip connections and residual connections is used to enhance the robustness of the model through multi-scale output, and finally, Moir é fringes are removed through weighted convolutional layers. The experimental results show that the evaluation scores of the model on three public datasets, UHDM, TIP, and FHDMI, are better than those of mainstream models for removing image moir é patterns, proving that the model effectively improves the effectiveness of image moir é pattern removal. |
| Keywords: | Image Moir é Removal; Weighted Convolution; Multi-scale Attention; UNet |
基金
| 1. | 国家社会科学基金一般项目 (20BMZ092) |
参考文献
| [1] | 亓文法, 刘宇鑫, 郭宗明. 摩尔纹图案自动去除技术综述 [J]. 计算机研究与发展, 2024, 61(03): 728-747. |
| [2] | Sun B, Li S, Sun J. Scanned image descreening with image redundancy and adaptive filtering [J]. IEEE transactions on image processing, 2014, 23(8): 3698-3710. |
| [3] | Wei Z, Wang J, Nichol H, et al. A median-Gaussian filtering framework for Moiré pattern noise removal from X-ray microscopy image [J]. Micron, 2012, 43(2-3): 170-176. |
| [4] | Sidorov D N, Kokaram A C. Removing moire from degraded video archives [C] // 2002 11th European Signal Processing Conference. IEEE, 2002: 1-4. |
| [5] | Kimmel R. Demosaicing: Image reconstruction from color CCD samples [J]. IEEE Transactions on image processing, 1999, 8(9): 1221-1228. |
| [6] | 邱菊. 基于插值算法的去彩色摩尔纹效应的研究 [D]. 南京理工大学, 2009. |
| [7] | 邱香香. 基于 CCD 静态图像的摩尔纹去除算法研究 [D]. 南京理工大学, 2012. |
| [8] | Sun Y, Yu Y, Wang W. Moiré photo restoration using multiresolution convolutional neural networks [J]. IEEE Transactions on Image Processing, 2018, 27(8): 4160-4172. |
| [9] | Gao T, Guo Y, Zheng X, et al. Moiré pattern removal with multi-scale feature enhancing network [C] // 2019 IEEE International Conference on Multimedia & Expo Workshops (ICMEW). IEEE, 2019: 240-245. |
| [10] | Zheng B, Yuan S, Slabaugh G, et al. Image demoireing with learnable bandpass filters [C] // Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 3636-3645. |
| [11] | He B, Wang C, Shi B, et al. Mop moire patterns using mopnet [C] // Proceedings of the IEEE/CVF international conference on computer vision. 2019: 2424-2432. |
| [12] | Dong C, Loy C C, He K, et al. Learning a deep convolutional network for image super-resolution [C] // European conference on computer vision. Cham: Springer International Publishing, 2014: 184-199. |
| [13] | Kim J, Lee J K, Lee K M. Accurate image super-resolution using very deep convolutional networks [C] // Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 1646-1654. |
| [14] | Ledig C, Theis L, Huszár F, et al. Photo-realistic single image super-resolution using a generative adversarial network [C] // Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 4681-4690. |
| [15] | He B, Wang C, Shi B, et al. FHDe2Net: Full high definition demoireing network [C] // European Conference on Computer Vision. Cham: Springer International Publishing, 2020: 713-729. |
| [16] | Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation [C] // International Conference on Medical image computing and computer-assisted intervention. Cham: Springer international publishing, 2015: 234-241. |
| [17] | Cammarasana S, Patanè G. Optimal Weighted Convolution for Classification and Denosing [J]. arXiv preprint arXiv: 2505.24558, 2025. |
| [18] | Zhang K, Li Y, Liang J, et al. Practical blind image denoising via Swin-Conv-UNet and data synthesis [J]. Machine Intelligence Research, 2023, 20(6): 822-836. |
| [19] | Fan C M, Liu T J, Liu K H. SUNet: Swin transformer UNet for image denoising [C] // 2022 IEEE International Symposium on Circuits and Systems (ISCAS). IEEE, 2022: 2333-2337. |
| [20] | Gurrola-Ramos J, Dalmau O, Alarcon T E. A residual dense u-net neural network for image denoising [J]. IEEE Access, 2021, 9: 31742-31754. |
| [21] | Shi X P, Lin S Y, Yang M L, et al. Image deblurring by multi-scale modified U-Net using dilated convolution [J]. Science Progress, 2024, 107(1): 00368504241231161. |
| [22] | Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions [C] // Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 1-9. |
| [23] | Hu J, Shen L, Sun G. Squeeze-and-excitation networks [C] // Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7132-7141. |
| [24] | Sun L, Dong J, Tang J, et al. Spatially-adaptive feature modulation for efficient image super-resolution [C] // Proceedings of the IEEE/CVF international conference on computer vision. 2023: 13190-13199. |
| [25] | Yu X, Dai P, Li W, et al. Towards efficient and scale-robust ultra-high-definition image demoiréing [C] // European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2022: 646-662. |
