This study is to explore the effect of deep learning algorithms applied to the non-photorealistic rendering (NPR) of ink painting. The powerful processing capabilities of NPR technology and convolutional neural networks (CNN) in computer vision are analyzed. Aiming at the features of ink texture images, a new sample-based ink texture synthesis method is proposed. The feature representation of ink texture is calculated using the CNN model, and then an ink texture with the same feature representation is generated on a random image. In addition, a synthesis method of ink painting picture is proposed based on the CNN. The results show that the ink texture generated by the ink texture synthesis algorithm is very good, and the Visual Geometry Group Network (VGG-Net) model shows the best generation effect. For images generated by high-level networks lack a lot of pixel information, but retain the main feature information of the image. When the learning rate is 10, the effect of the ink image synthesized based on the content image is slightly worse; and the image generated by the fusion of multiple styles confirms the feasibility of synthesizing ink images of different "sizes and styles". Therefore, this ink image synthesized on the basis of the CNN model shows a better effect, which extends the possibility of computer creation of richer ink painting works.

Li Wang, Jaewoong Kim. Deep Learning in Computer Real-time Graphics and Image Using the Visual Effects of Non-photorealistic Rendering of Ink Painting. Frontiers in Art Research (2022) Vol. 4, Issue 15: 95-107. https://doi.org/10.25236/FAR.2022.041519.

[1] Sun D, Zhan R, Zhang J, et al. Realistic Story Visualization from Online Photo Collections [J]. Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics, 2018, 30(8):1479.

[2] Zhao Shaoyan. Style analysis of Wang Yuan's ink painting of flowers and birds [J]. Fine arts, 2019, 000 (002): 134-135.

[3] Zhang F, Gao H, Lai Y. Detail-Preserving CycleGAN-AdaIN Framework for Image-to-Ink Painting Translation [J]. IEEE Access, 2020, PP (99):1-1.

[4] Hauptfleisch F, Texler O, Texler A, et al. StyleProp: Real-time Example-based Stylization of 3D Models [J]. Computer Graphics Forum, 2020, 39(7):575-586. 

[5] Huang L, Hou Z X, Zhao Y H, et al. Research progress on and prospects for virtual brush modeling in digital calligraphy and painting[J]. Frontiers of Information Technology & Electronic Engineering, 2019, 20(10):1307-1321.

[6] Zheng Y, Chen Y, Sarem M. A Novel Pencil Drawing Algorithm Based on Non-Symmetry and Anti-Packing Pattern Representation Model [J]. IEEE Access, 2019, 7:1-1.

[7] Kumar M, Poornima B, Nagendraswamy H S, et al. A comprehensive survey on non-photorealistic rendering and benchmark developments for image abstraction and stylization [J]. Iran Journal of Computer Science, 2019, 2(3):131-165.

[8] Montesdeoca S E, Seah H S, Semmo A, et al. Mnpr: A framework for real-time expressive non-photorealistic rendering of 3d computer graphics[C]//Proceedings of the Joint Symposium on Computational Aesthetics and Sketch-Based Interfaces and Modeling and Non-Photorealistic Animation and Rendering. 2018: 1-11.

[9] Bakurov I, Ross B J. Non-photorealistic rendering with cartesian genetic programming using graphics processing units[C]//International Conference on Computational Intelligence in Music, Sound, Art and Design. Springer, Cham, 2018: 34-49. 

[10] Qian W, Cao J, Xu D, et al. Research status and Prospect of nonphotorealistic rendering technology [J]. Chinese Journal of image graphics, 2020 (7): 1283-1295.

[11] Liu A, Zhao Z, Zhang C, et al. Smooth filtering identification based on convolutional neural networks[J]. Multimedia Tools and Applications, 2019, 78(19):26851-26865.

[12] Seddiki K, Saudemont P, Precioso F, et al. Cumulative learning enables convolutional neural network representations for small mass spectrometry data classification[J]. Nature Communications, 2020, 11(1).

[13] Tan M, Li J, Xu G, et al. A Novel Intuitionistic Fuzzy Inhibitor Arc Petri Net with Error Back Propagation Algorithm and Application in Fault Diagnosis [J]. IEEE Access, 2019, PP (99):1-1.

[14] Wang J, H Wu, Zhang X, et al. Watermarking in Deep Neural Networks via Error Back-propagation[J]. Electronic Imaging, 2020, 2020(4):22-1-22-9.

[15] Zeng J L, Chen K H, Wang J Y. High-Performance Vlsi Design For Convolution Layer Of Deep Learning Neural Networks[J]. Journal of electrical engineering, 2019, 26(5):195-202.

[16] Zhang T, Hu D, Zhang J. Scale Adaptive Block Target Tracking Based on Multi-layer Convolution Features and Kernel Correlation Filter[J]. Journal of Physics Conference Series, 2021, 1828(1):012042.

[17] Leclaire A, Rabin J. A Stochastic Multi-laryer Algorithm for Semi-discrete Optimal Transport with Applications to Texture Synthesis and Style Transfer [J]. Journal of Mathematical Imaging and Vision, 2021, 63(2):282-308.

[18] Chen Q, Li G, Xie L, et al. Structure guided image completion using texture synthesis and region segmentation[J]. Optik, 2019, 185:896-909.

[19] Al-Jaberi A K, Hameed E M. A Review of PDE Based Local Inpainting Methods [J]. Journal of Physics Conference Series, 2021, 1818(1):012149.

[20] Badawi A A, Chao J, Jie L, et al. The AlexNet Moment for Homomorphic Encryption: HCNN, the First Homomorphic CNN on Encrypted Data with GPUs [J]. IEEE Transactions on Emerging Topics in Computing, 2020, PP (99):1-1.

[21] Xie S, Zheng X, Chen Y, et al. Artifact Removal using Improved GoogLeNet for Sparse-view CT Reconstruction[J]. Scientific Reports, 2018, 8(1):6700.

[22] Amir S, Faturrahman, Hendra. Hand posture classification with convolutional neural networks on VGG-net Architecture [J]. IOP Conference Series: Earth and Environmental Science, 2020, 575(1):012186 (8pp).

[23] Sehad A, Chibani Y, Hedjam R, et al. Gabor filter-based texture for ancient degraded document image binarization [J]. Pattern Analysis and Applications, 2019, 22(1):1-22.

[24] Dai Y, Li Y, Sun B, et al. Skip-Connected Network with Gram Matrix for Product Image Retrieval [J]. Neurocomputing, 2021, 447(3).

[25] Deng s, Che X. GPU based 3D model rendering of Chinese ink painting [J]. Computer aided graphic design and manufacturing (English version), 2017 (1): 1-6.

[26] Cho S W, Na R B, Koo J H, et al. Semantic Segmentation with Low light Images by Modified CycleGAN-based Image Enhancement [J]. IEEE Access, 2020, PP (99):1-1.

[27] Zhang L, Technology of Low Contrast Printing Defects Based on Enhancement. Packaging Engineering, 2019, 40(13):252-258.

[28] Liang Y, Liu W, Yi S, et al. Filter pruning-based two-step feature map reconstruction [J]. Signal Image and Video Processing, 2021(2).

[29] Hababeh I, Mahameed I, Abdelhadi A, et al. Utilizing Convolutional Neural Networks for Image Classification and Securing Mobility of People with Physical and Mental Disabilities in Cloud Systems[J]. IEEE Access, 2020, PP (99):1-1.

[30] Xin Y, Jwab C, Wei H. Hybrid fuzzy integrated convolutional neural network (HFICNN) for similarity feature recognition problem in abnormal netflow detection [J]. Neurocomputing, 2020, 415:332-346.