计算机科学 ›› 2019, Vol. 46 ›› Issue (3): 283-286.doi: 10.11896/j.issn.1002-137X.2019.03.042
刘洪麟,帅仁俊
LIU Hong-lin, SHUAI Ren-jun
摘要: 在神经风格迁移(Neural Style Transfer)技术中常用Gram矩阵进行图像风格提取,简单来说就是将各个特征进行内积。这样Gram矩阵只能提取其静态特征,对图片中物体的空间序列完全没有约束。文中提出了一种具有空间约束的快速神经风格迁移方法。首先,使用残差重新设计了快速神经风格迁移的转换网络。然后,运用空间偏移的方法对Feature map(特征图)进行变换,让变换后的Feature map T(al)进行Gram矩阵计算可得到相邻位置的互相关性。此互相关性包含空间信息,即约束了物体的空间序列。最终,实验表明了该方法对空间信息的约束明显优于传统方法,可以得到效果更好的风格化图像。
中图分类号:
[1]DENG Y Y,TANG F,DONG W M.The status research of styli- zation of art image[J].Journal of Nanjing University of Information Technology(Natural Science Edition),2017,9(6):593-598.(in Chinese) 邓盈盈,唐帆,董未名.图像艺术风格化的研究现状[J].南京信息工程大学学报(自然科学版),2017,9(6):593-598. [2]GATYS L A,ECKER A S,BETHGE M.A neural algorithm of artistic style[J].Computer Science,2015,111(1):98-136. [3]GATYS L A,ECKER A S,BETHGE M.Image style transfer using convolutional neural networks[C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2016:2414-2423. [4]WILMOT P,RISSER E,BARNES C.Stable and controllable neural texture synthesis and style transfer using histogram losses[J].Computer Science,2017,15(1):96-140. [5]JOHNSON J,ALAHI A,FEI-FEI L.Perceptual losses for real-time style transfer and super-resolution[C]∥EuropeanConfe-rence on Computer Vision.Springer,Cham,2016:694-711. [6]ULYANOV D,VEDALDI A,LEMPITSKY V.Improved tex- ture networks:Maximizing quality and diversity in feed-forward stylization and texture synthesis[C]∥The IEEE Conference on Computer Vision and Pattern Recognition.2017. [7]CAO J F.Research and Implementation of Stylization of Image and Video Based on Deep Learning[D].Beijing:Chinese Academy of Sciences University,2017.(in Chinese) 操江峰.基于深度学习的图像与视频风格化研究与实现[D].北京:中国科学院大学,2017. [8]MAHENDRAN A,VEDALDI A.Understanding deep image representations by inverting them[C]∥Proceedings of the IEEE Conference on Computer Vision and PatternRecognition (CVPR).2015. [9]CHIKONTWE P,LEE H J.Towards Robust Face Sketch Synthesis with Style Transfer Algorithms[M]∥IT Convergence and Security 2017.Singapore:Springer,2018:172-179. [10]ZHU J Y,KRHENBHL P,SHECHTMAN E,et al.Generative visual manipulation on the natural image manifold[C]∥European Conference on Computer Vision.Springer,Cham,2016:597-613. [11]LV L Z,QIANG Y.Medical CT Image Enhancement Algorithm Based on Laplacian Pyramid and Wavelet Transform[J].Computer Science,2016,43(11):300-303.(in Chinese) 吕鲤志,强彦.基于Laplacian金字塔和小波变换的医学CT图像增强算法[J].计算机科学,2016,43(11):300-303. [12]IGNATOV A,KOBYSHEV N,VANHOEY K,et al.DSLR- quality photos on mobile devices with deep convolutional networks[C]∥The IEEE International Conference on Computer Vision (ICCV).2017. |
[1] | 王馨彤, 王璇, 孙知信. 基于多尺度记忆残差网络的网络流量异常检测模型 Network Traffic Anomaly Detection Method Based on Multi-scale Memory Residual Network 计算机科学, 2022, 49(8): 314-322. https://doi.org/10.11896/jsjkx.220200011 |
[2] | 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 |
[3] | 张嘉淏, 刘峰, 齐佳音. 一种基于Bottleneck Transformer的轻量级微表情识别架构 Lightweight Micro-expression Recognition Architecture Based on Bottleneck Transformer 计算机科学, 2022, 49(6A): 370-377. https://doi.org/10.11896/jsjkx.210500023 |
[4] | 韩红旗, 冉亚鑫, 张运良, 桂婕, 高雄, 易梦琳. 基于共同子空间分类学习的跨媒体检索研究 Study on Cross-media Information Retrieval Based on Common Subspace Classification Learning 计算机科学, 2022, 49(5): 33-42. https://doi.org/10.11896/jsjkx.210200157 |
[5] | 高元浩, 罗晓清, 张战成. 基于特征分离的红外与可见光图像融合算法 Infrared and Visible Image Fusion Based on Feature Separation 计算机科学, 2022, 49(5): 58-63. https://doi.org/10.11896/jsjkx.210200148 |
[6] | 赵人行, 徐频捷, 刘瑶. 基于深度卷积残差网络的心电单导联房颤检测方法 ECG-based Atrial Fibrillation Detection Based on Deep Convolutional Residual Neural Network 计算机科学, 2022, 49(5): 186-193. https://doi.org/10.11896/jsjkx.220200002 |
[7] | 高心悦, 田汉民. 基于改进U-Net网络的液滴分割方法 Droplet Segmentation Method Based on Improved U-Net Network 计算机科学, 2022, 49(4): 227-232. https://doi.org/10.11896/jsjkx.210300193 |
[8] | 张红民, 李萍萍, 房晓冰, 刘宏. 改进YOLOv3网络模型的人体异常行为检测方法 Human Abnormal Behavior Detection Method Based on Improved YOLOv3 Network Model 计算机科学, 2022, 49(4): 233-238. https://doi.org/10.11896/jsjkx.210300251 |
[9] | 瞿中, 陈雯. 基于空洞卷积和多特征融合的混凝土路面裂缝检测 Concrete Pavement Crack Detection Based on Dilated Convolution and Multi-features Fusion 计算机科学, 2022, 49(3): 192-196. https://doi.org/10.11896/jsjkx.210100164 |
[10] | 张侣, 周博文, 吴亮红. 基于改进卷积注意力模块与残差结构的SSD网络 SSD Network Based on Improved Convolutional Attention Module and Residual Structure 计算机科学, 2022, 49(3): 211-217. https://doi.org/10.11896/jsjkx.201200019 |
[11] | 周文辉, 石敏, 朱登明, 周军. 基于残差注意力网络的地震数据超分辨率方法 Seismic Data Super-resolution Method Based on Residual Attention Network 计算机科学, 2021, 48(8): 24-31. https://doi.org/10.11896/jsjkx.200900034 |
[12] | 郭琳, 李晨, 陈晨, 赵睿, 范仕霖, 徐星雨. 基于通道注意递归残差网络的图像超分辨率重建 Image Super-resolution Reconstruction Using Recursive ResidualNetwork Based on ChannelAttention 计算机科学, 2021, 48(8): 139-144. https://doi.org/10.11896/jsjkx.200500150 |
[13] | 许华杰, 张晨强, 苏国韶. 基于深层卷积残差网络的航拍图建筑物精确分割方法 Accurate Segmentation Method of Aerial Photography Buildings Based on Deep Convolutional Residual Network 计算机科学, 2021, 48(8): 169-174. https://doi.org/10.11896/jsjkx.200500096 |
[14] | 暴雨轩, 芦天亮, 杜彦辉, 石达. 基于i_ResNet34模型和数据增强的深度伪造视频检测方法 Deepfake Videos Detection Method Based on i_ResNet34 Model and Data Augmentation 计算机科学, 2021, 48(7): 77-85. https://doi.org/10.11896/jsjkx.210300258 |
[15] | 牛康力, 谌雨章, 张龚平, 谭前程, 王绎冲, 罗美琪. 基于深度学习的无人机航拍车流量监测 Vehicle Flow Measuring of UVA Based on Deep Learning 计算机科学, 2021, 48(6A): 275-280. https://doi.org/10.11896/jsjkx.200900149 |
|