计算机科学 ›› 2020, Vol. 47 ›› Issue (8): 202-207.doi: 10.11896/jsjkx.190700017
孟丽莎, 任坤, 范春奇, 黄泷
MENG Li-sha, REN Kun, FAN Chun-qi, HUANG Long
摘要: 图像修复是一项利用缺损图像中已知信息对缺损区域信息进行估计修复的技术。针对大面积语义信息缺失的图像进行修复时, 若训练数据集较小且图像背景相对复杂, 则基于生成模型的修复结果常出现模糊、伪影和视觉相似度差等问题。针对上述问题, 文中提出了一种基于密集卷积生成对抗网络的图像修复算法。该算法采用生成对抗网络作为图像修复的基本框架。首先, 利用密集卷积块构建具有编解码结构的生成网络, 不但加强了图像特征的提取, 提高了图像修复能力, 而且避免了深度增加引起的梯度消失问题。其次, 在编码和解码结构之间引入跳跃连接, 解决了网络层间信息传递丢失的问题。然后, 在网络优化过程中, 结合重建损失、对抗损失和TV损失来训练网络模型, 增强了网络稳定性。最后, 分别在CelebA和Car两个数据集上进行实验, 所提算法的修复结果在视觉效果、峰值信噪比PSNR和结构相似度SSIM 3个方面均优于3种代表性图像修复算法, 其有效性得到验证。
中图分类号:
[1]BERTALMIO M, SAPIRO G, CASELLESV, et al.Image in-painting[C]∥Conference on Computer Graphics and Interactive Techniques.ACM Press/Addison-Wesley Publishing Company, 2000:417-424. [2]PETERSON I.Filling in Blanks:Automating the Inpainting of a Picture's Missing Pieces [J].Science News, 2002, 161(19):299-300. [3]CRIMINISI A, PEREZ P, TOYAMA K.Region Filling and Object Removal by Exemplar-based Image Inpainting [J].IEEE Transactions on Image Processing, 2004, 13(9):1200-1212. [4]GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al.Gene-rative Adversarial Nets[C]∥International Conference on Neural Information Procession Systems.2014:2672-2680. [5]PATHAK D, KRAHENBUHL P, DONAHUE J, et al.Context Encoders:Feature Learning by Inpainting[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:2536-2544. [6]YEH R A, CHEN C, LIM T Y, et al.Semantic Image Inpainting with Deep Generative Models[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:6882-6890。 [7]ZHAO G, LIU J, JIANG J, et al.A Deep Cascade of Neural Networks for Image Inpainting, Deblurring and Denoising [J].Multimedia Tools and Applications, 2018, 77(22):29589-29604. [8]ALTINEL F, OZAY M, OKATANI T.Deep Structured Energy-Based Image Inpainting [C]∥2018 24th International Confe-rence on Pattern Recognition (ICPR).Beijing, 2018:423-428. [9]YU J, LIN Z, YANG J, et al.Generative Image Inpainting with Contextual Attention[C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).IEEE, 2018:5505-5514 [10]RONNEBERGER O, FISCHER P, BROX T.U-Net:Convolu-tional Networks for Biomedical Image Segmentation[C]∥Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention.Cham:Sprin-ger, 2015:234-241. [11]DOSOVISKIY A, BROX T.Generating Images with Perceptual Similarity Metrics based on Deep Networks [C]∥Advances in Neural Information Processing Systems.2016:658-666. [12]ISOLA P, ZHU J Y, ZHOU T, et al.Image-to-Image Translation with Conditional Adversarial Networks [C]∥Computer Vision and Pattern Recognition.2016:5967-5976. [13]LI C, WAND M.Precomputed Real-Time Texture Synthesiswith Markovian Generative Adversarial Networks[C]∥Euro-pean Conference on Computer Vision.2016:702-716. [14]LEDIG C, THEIS L, HUSZAR F, CABALLERO J, et al.Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network [C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Honolulu, HI, 2017:105-114. [15]HUANG G, LIU Z, MAATEN L V D, et al.Densely Connected Convolutional Networks[C]∥IEEE Conference on Computer Vision and Pattern Recognition.IEEE Computer Society, 2017:2261-2269 [16]KINGMA D P, WELLING M.Auto-Encoding Variational Bayes [C]∥Proceedings of the International Conference on Learning Representations (ICLR).2014. [17]AKAIKE H.Fitting Autoregressive Models for Prediction [J].Annals of the Institute of Statistical Mathematics, 1969, 21(1):243-247. [18]HINTON G E, OSINDEROS S, TEH Y W.A Fast Learning Al-gorithm for Deep Belief Nets [J].Neural Computation, 2006, 18(7):1527-1554. [19]RADFORD A, METZ L, CHINTALA S.Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks [J].arXiv:1511.06434, 2015. [20]JAVANMARDI M, SAJJADI M, LIU T, et al.UnsupervisedTotal Variation Loss for Semi-supervised Deep Learning of Semantic Segmentation [J].arXiv:1605.01368v3, 2016 |
[1] | 张佳, 董守斌. 基于评论方面级用户偏好迁移的跨领域推荐算法 Cross-domain Recommendation Based on Review Aspect-level User Preference Transfer 计算机科学, 2022, 49(9): 41-47. https://doi.org/10.11896/jsjkx.220200131 |
[2] | 孙奇, 吉根林, 张杰. 基于非局部注意力生成对抗网络的视频异常事件检测方法 Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection 计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061 |
[3] | 戴朝霞, 李锦欣, 张向东, 徐旭, 梅林, 张亮. 基于DNGAN的磁共振图像超分辨率重建算法 Super-resolution Reconstruction of MRI Based on DNGAN 计算机科学, 2022, 49(7): 113-119. https://doi.org/10.11896/jsjkx.210600105 |
[4] | 孟月波, 穆思蓉, 刘光辉, 徐胜军, 韩九强. 基于向量注意力机制GoogLeNet-GMP的行人重识别方法 Person Re-identification Method Based on GoogLeNet-GMP Based on Vector Attention Mechanism 计算机科学, 2022, 49(7): 142-147. https://doi.org/10.11896/jsjkx.210600198 |
[5] | 高荣华, 白强, 王荣, 吴华瑞, 孙想. 改进注意力机制的多叉树网络多作物早期病害识别方法 Multi-tree Network Multi-crop Early Disease Recognition Method Based on Improved Attention Mechanism 计算机科学, 2022, 49(6A): 363-369. https://doi.org/10.11896/jsjkx.210500044 |
[6] | 尹文兵, 高戈, 曾邦, 王霄, 陈怡. 基于时频域生成对抗网络的语音增强算法 Speech Enhancement Based on Time-Frequency Domain GAN 计算机科学, 2022, 49(6): 187-192. https://doi.org/10.11896/jsjkx.210500114 |
[7] | 徐辉, 康金梦, 张加万. 基于特征感知的数字壁画复原方法 Digital Mural Inpainting Method Based on Feature Perception 计算机科学, 2022, 49(6): 217-223. https://doi.org/10.11896/jsjkx.210500105 |
[8] | 高志宇, 王天荆, 汪悦, 沈航, 白光伟. 基于生成对抗网络的5G网络流量预测方法 Traffic Prediction Method for 5G Network Based on Generative Adversarial Network 计算机科学, 2022, 49(4): 321-328. https://doi.org/10.11896/jsjkx.210300240 |
[9] | 黎思泉, 万永菁, 蒋翠玲. 基于生成对抗网络去影像的多基频估计算法 Multiple Fundamental Frequency Estimation Algorithm Based on Generative Adversarial Networks for Image Removal 计算机科学, 2022, 49(3): 179-184. https://doi.org/10.11896/jsjkx.201200081 |
[10] | 石达, 芦天亮, 杜彦辉, 张建岭, 暴雨轩. 基于改进CycleGAN的人脸性别伪造图像生成模型 Generation Model of Gender-forged Face Image Based on Improved CycleGAN 计算机科学, 2022, 49(2): 31-39. https://doi.org/10.11896/jsjkx.210600012 |
[11] | 唐雨潇, 王斌君. 基于深度生成模型的人脸编辑研究进展 Research Progress of Face Editing Based on Deep Generative Model 计算机科学, 2022, 49(2): 51-61. https://doi.org/10.11896/jsjkx.210400108 |
[12] | 李建, 郭延明, 于天元, 武与伦, 王翔汉, 老松杨. 基于生成对抗网络的多目标类别对抗样本生成算法 Multi-target Category Adversarial Example Generating Algorithm Based on GAN 计算机科学, 2022, 49(2): 83-91. https://doi.org/10.11896/jsjkx.210800130 |
[13] | 谈馨悦, 何小海, 王正勇, 罗晓东, 卿粼波. 基于Transformer交叉注意力的文本生成图像技术 Text-to-Image Generation Technology Based on Transformer Cross Attention 计算机科学, 2022, 49(2): 107-115. https://doi.org/10.11896/jsjkx.210600085 |
[14] | 陈贵强, 何军. 自然场景下遥感图像超分辨率重建算法研究 Study on Super-resolution Reconstruction Algorithm of Remote Sensing Images in Natural Scene 计算机科学, 2022, 49(2): 116-122. https://doi.org/10.11896/jsjkx.210700095 |
[15] | 蒋宗礼, 樊珂, 张津丽. 基于生成对抗网络和元路径的异质网络表示学习 Generative Adversarial Network and Meta-path Based Heterogeneous Network Representation Learning 计算机科学, 2022, 49(1): 133-139. https://doi.org/10.11896/jsjkx.201000179 |
|