计算机科学 ›› 2019, Vol. 46 ›› Issue (1): 100-106.doi: 10.11896/j.issn.1002-137X.2019.01.015
徐强, 钟尚平, 陈开志, 张春阳
XU Qiang, ZHONG Shang-ping, CHEN Kai-zhi, ZHANG Chun-yang
摘要: 高质量的图像生成一直是计算机视觉等领域探索的难点和热点。通过使用循环一致损失,CycleGAN在无监督图像生成任务中取得了良好效果。但是面对不同纹理复杂度的图像生成任务,CycleGAN的循环一致损失系数是默认不变的,使得生成图像存在纹理变形甚至消失等弱点,不能很好地保证生成图像的质量。文中融合图像的空间维度和时间维度来度量图像的纹理复杂性,阐明循环一致损失函数在优化目标函数中的重要性,发现并解释循环一致损失系数的大小与不同纹理复杂度图像生成质量的关联性:纹理复杂度越高,应选择越大的循环一致损失系数;反之,应取越小的循环一致损失系数。文中使用基准和自采集的图像数据集,引入了基于迁移学习的分类准确性等生成图像质量评估指标。实验结果表明,优化选择大小合适的循环一致损失系数,可有效提高生成图像的质量。
中图分类号:
[1]LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE,2015:3431-3440.<br /> [2]GATYS L,ECKER A S,BETHGE M.Texture synthesis using convolutional neural networks[C]//Advances in Neural Information Processing Systems.Cambridge,Massachusetts:MIT Press,2015:262-270.<br /> [3]GATYS L A,ECKER A S,BETHGE M.Image style transfer using convolutional neural networks//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway,NJ:IEEE,2016:2414-2423.<br /> [4]JOHNSON J,ALAHI A,FEI-FEI L.Perceptual losses for real-time style transfer and super-resolution[C]//European Con-ference on Computer Vision.Berlin,German:Springer,2016:694-711.<br /> [5]NASH J.Non-Cooperative Games.Annals of Mathematics,1951,54(2):286-295.<br /> [6]GOODFELLOW I J,POUGET-ABADIE J,MIRZA M,et al.Generative adversarial nets[C]//International Conference on Neural Information Processing Systems.Cambridge,Massachusetts:MIT Press,2014:2672-2680.<br /> [7]DENTON E L,CHINTALA S,FERGUS R.Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks[C]//Advances in Neural Information Processing Systems.Cambridge,Massachusetts:MIT Press,2015:1486-1494.<br /> [8]LI C,WAND M.Precomputed real-time texture synthesis with markovian generative adversarial networks[C]//European Conference on Computer Vision.Berlin,German:Springer,2016:702-716.<br /> [9]LI C,ZHAO X Y,XIAO L M,et al.Multi-layer perceptual defogging algorithm for image under generative adversarial networks[J].Journal of Computer-Aided Design & Computer Graphics,2017,29(10):1835-1843.(in Chinese)<br /> 李策,赵新宇,肖利梅,等.生成对抗映射网络下的图像多层感知去雾算法[J].计算机辅助设计与图形学学报,2017,29(10):1835-1843.<br /> [10]LEDIG C,WANG Z,SHI W,et al.Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network//Computer Vision and Pattern Recognition.IEEE,2017:105-114.<br /> [11]MIRZA M,OSINDERO S.Conditional generative adversarial nets.arXiv preprint arXiv:1411.1784,2014.<br /> [12]ZHU J Y,KRÄHENBÜHL P,SHECHTMAN E,et al.Generative visual manipulation on the natural image manifold[C]//European Conference on Computer Vision.Berlin,German:Sprin-ger,2016:597-613.<br /> [13]ISOLA P,ZHU J Y,ZHOU T,et al.Image-to-Image Translation with Conditional Adversarial Networks[C]//IEEE Con-ference on Computer Vision and Pattern Recognition.Pisca-taway,NJ:IEEE,2017:5967-5976.<br /> [14]RADFORD A,METZ L,CHINTALA S.Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks[J].arXiv:1511.06434.2016.<br /> [15]FUKUSHIMA K.Neural network model for a mechanism of pattern recognition unaffected by shift in position-Neocognitron[J].IEICE Technical Report A,1979,62(10):658-665.<br /> [16]YI Z,ZHANG H,TAN P,et al.DualGAN:Unsupervised Dual Learning for Image-to-Image Translation[C]//IEEE International Conference on Computer Vision.Piscataway,NJ:IEEE,2017:2868-2876.<br /> [17]ARJOVSKY M,CHINTALA S,BOTTOU L.Wasserstein GAN[J].arXiv preprint arXiv:1701.07875,2017.<br /> [18]GOLDSTEIN T,OSHER S.The split Bregman method for L1-regularized problems[J].SIAM Journal on Imaging Sciences,2009,2(2):323-343.<br /> [19]KIM T,CHA M,KIM H,et al.Learning to Discover Cross-Domain Relations with Generative Adversarial Networks[C]//Proceedings of the 34th International Conference on Machine Learning.New York:ACM,2017:1857-1865.<br /> [20]ZHU J Y,PARK T,ISOLA P,et al.Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks[C]//IEEE International Conference on Computer Vision.Piscata-way,NJ:IEEE,2017:2242-2251.<br /> [21]HE D,XIA Y,QIN T,et al.Dual learning for machine translation[C]//Advances in Neural Information Processing Systems.Cambridge,Massachusetts:MIT Press,2016:820-828.<br /> [22]ZHOU T,KRAHENBUHL P,AUBRY M,et al.Learning dense correspondence via 3d-guided cycle consistency[C]//Procee-dings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE,2016:117-126.<br /> [23]CARDACI M,DI GESÙ V,PETROU M,et al.A fuzzy approach to the evaluation of image complexity[J].Fuzzy Sets and Systems,2009,160(10):1474-1484.<br /> [24]RUSSAKOVSKY O,DENG J,SU H,et al.Imagenet large scale visual recognition challenge[J].International Journal of Computer Vision,2015,115(3):211-252.<br /> [25]SZEGEDY C,VANHOUCKE V,IOFFE S,et al.Rethinking the inception architecture for computer vision[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE,2016:2818-2826.<br /> [26]WANG X,GUPTA A.Generative image modeling using style and structure adversarial networks[C]//European Conference on Computer Vision.Berlin,German:Springer,2016:318-335.<br /> [27]MAO X,LI Q,XIE H,et al.Least squares generative adversarial networks//2017 IEEE International Conference on ComputerVision (ICCV).IEEE,2017:2813-2821.<br /> [28]SABOUR S,FROSST N,HINTON G E.Dynamic routing between capsules[C]//Advances in Neural Information Processing Systems.Berlin,German:MIT Press,2017:3859-3869.<br /> [29]LEEUWENBERG E,BUFFART H.An outline of coding theory[J].Advances in psychology,1983,11:25-47.<br /> [30]SU H,BOURIDANE A,CROOKES D.Scale Adaptive Complexity Measure of 2D Shapes//International Conference on Pattern Recognition.Piscataway,NJ:IEEE,2006:134-137.<br /> [31]PAN S J,YANG Q.A survey on transfer learning[J].IEEE Transactions on knowledge and data engineering,2010,22(10):1345-1359.<br /> [32]ZHOU B,LAPEDRIZA A,XIAO J,et al.Learning deep features for scene recognition using places database[C]//Advances in neural information processing systems.Cambridge,Massachusetts:MIT Press,2014:487-495.<br /> [33]GARCIA B, BRUNET P.3D reconstruction with projective octrees and epipolar geometry//International Conference on Computer Vision.Piscataway,NJ: IEEE,2008:1067-1072. |
[1] | 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 |
[2] | 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 |
[3] | 崔雯昊, 蒋慕蓉, 杨磊, 傅鹏铭, 朱凌霄. 结合MCycleGAN与RFCNN实现太阳斑点图高分辨重建 Combining MCycleGAN and RFCNN to Realize High Resolution Reconstruction of Solar Speckle Image 计算机科学, 2021, 48(6A): 38-42. https://doi.org/10.11896/jsjkx.201000160 |
[4] | 胡妤婕, 常建慧, 张健. 语义区域风格约束下的图像合成 Image Synthesis with Semantic Region Style Constraint 计算机科学, 2021, 48(2): 134-141. https://doi.org/10.11896/jsjkx.200800201 |
[5] | 张扬, 马小虎. 基于改进生成对抗网络的动漫人物头像生成算法 Anime Character Portrait Generation Algorithm Based on Improved Generative Adversarial Networks 计算机科学, 2021, 48(1): 182-189. https://doi.org/10.11896/jsjkx.191100092 |
[6] | 叶亚男, 迟静, 于志平, 战玉丽, 张彩明. 基于改进CycleGan模型和区域分割的表情动画合成 Expression Animation Synthesis Based on Improved CycleGan Model and Region Segmentation 计算机科学, 2020, 47(9): 142-149. https://doi.org/10.11896/jsjkx.190900203 |
[7] | 周兵, 刘玉霞, 杨欣欣, 刘扬. 图像复杂度研究综述 Review of Research on Image Complexity 计算机科学, 2018, 45(9): 30-37. https://doi.org/10.11896/j.issn.1002-137X.2018.09.004 |
[8] | 李清,李东晖. 基于模糊逻辑的无损彩色图像压缩算法 Lossless Color Image Compression Method Based on Fuzzy Logic 计算机科学, 2014, 41(Z11): 103-106. |
[9] | 张芹 吴慧中 张健. 基于粒子系统的建模方法研究 计算机科学, 2003, 30(8): 144-146. |
[10] | 王建华 解凯. 基于图像的图形生成系统中的虚拟摄像机模型 计算机科学, 2002, 29(12): 160-161. |
|