Automatic generation of Chinese mural line drawings via enhanced edge detection and CycleGAN-based denoising
Source abstract
Abstract
Murals are a vital form of traditional Chinese art, rich in historical and cultural content. Line drawing, as a core technique, is widely used but still depends on manual tracing. This paper proposes an automatic method for generating mural line drawings by integrating edge enhancement, neural edge detection, and denoising. Enhance edges using image processing techniques, followed by a neural network (MLineNet) for line extraction. A cycle-consistent generative adversarial network (CycleGAN) refines the output by removing noise while preserving structural clarity. The model was evaluated using four metrics: structural similarity index (SSIM), texture complexity (TC), line connectivity index (LCI), and a comprehensive score ( Q ). On Dunhuang murals, it achieved scores of 89.54%, 93.77%, 88.14%, and 90.48%, respectively, and showed generalization to Baisha murals ( Q = 89.29%). Results demonstrate the method’s reliability in producing complete, clean, and continuous mural line drawings.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Medical Image Segmentation Techniques · Computer Graphics and Visualization Techniques · Industrial Vision Systems and Defect Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (55)
Show source-provided references
1. Ren, Y. & Liu, F. A model for inversion of hyperspectral characteristics of phosphate content in mural plaster based on fractional-order differential algorithm. Sci. Rep. 14, 17898 (2024).10.1038/s41598-024-68594-2 ↗
2. Lyu, Q., Zhao, N., Song, J., Yang, Y. & Gong, Y. Mural inpainting via two-stage generative adversarial network. npj Herit. Sci. 13, 188 (2025).10.1038/s40494-025-01710-1 ↗
3. Shen, J. et al. An algorithm based on lightweight semantic features for ancient mural element object detection. npj Herit. Sci. 13, 70 (2025).10.1038/s40494-025-01565-6 ↗
4. Guo, Q. The expression of lines in mural painting in Chinese meticulous figure painting. Front. Art. Res. 5, 69–73 (2023).
5. Cheng, Y., Huang, M. & Sun, W. VR-based line drawing methods in Chinese painting. In Proc. 2023 9th Int. Conf. Virtual Reality (ICVR) (eds Huang, X.) pp. 604–610 (IEEE, Xianyang, CN, 2023).10.1109/ICVR57957.2023.10169222 ↗
6. Zhang, J. J., Chen, J. N., Meng, D. Y. & Wang, X. C. Exploring the uncertainty principle in neural networks through binary classification. Sci. Rep. 14, 28402 (2024).10.1038/s41598-024-79028-4 ↗
7. Jing, J., Liu, S., Wang, G., Zhang, W. & Sun, C. Recent advances on image edge detection: a comprehensive review. Neurocomputing 503, 259–271 (2022).10.1016/j.neucom.2022.06.083 ↗
8. Amer, G. & Abushaala, A. M. Edge detection methods. In Proc. 2015 2nd World Symp. Web Appl. Netw. (WSWAN) (ed. Tagoug, N.) pp. 1–7 (ITI, Piscataway, NJ, USA, 2015).10.1109/WSWAN.2015.7210349 ↗
9. Çapkan, Y., Altun, H. & Fidan, C. B. Edge detection method driven by knowledge-based neighborhood rules. Int. J. Eng. Technol. Innov. 13, 01–13 (2023).10.46604/ijeti.2023.9710 ↗
10. Ye, Y., Xu, K., Huang, Y., Yi, R. & Cai, Z. DiffusionEdge: diffusion probabilistic model for crisp edge detection. Proc. AAAI Conf. Artif. Intell. 38, 6675–6683 (2024).
11. Soria, X., Li, Y., Rouhani, M. & Sappa, A. D. Tiny and efficient model for the edge detection generalization. In Proc. IEEE/CVF Int. Conf. Comput. Vis. Workshops (ICCVW) (eds. Agapito, L., Berg, T., Kosecka, J., & Zelnik-Manor, L.) pp. 1356–1365 (IEEE, Paris, FR, 2023).10.1109/ICCVW60793.2023.00147 ↗
12. Yang, J., Price, B., Cohen, S., Lee, H. & Yang, M. H. Object contour detection with a fully convolutional encoder-decoder network. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) (eds Agapito, L., Berg, T., Kosecka, J., Zelnik-Manor, L.) pp. 193–202 (IEEE Comput. Soc., Las Vegas, NV, USA, 2016).10.1109/CVPR.2016.28 ↗
13. Lisowska, A. Efficient edge detection method for focused images. Appl. Sci. 12, 11668 (2022).10.3390/app122211668 ↗
14. Pu, M., Huang, Y., Guan, Q. & Ling, H. B. RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depth. In Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV) (eds Agapito, L., Berg, T., Kosecka, J., Zelnik-Manor, L.) pp. 6879–6888 (IEEE Comput. Soc., Virtual Conf., 2021).10.1109/ICCV48922.2021.00680 ↗
15. Leng, K. et al. SuperEdge: towards a generalization model for self-supervised edge detection. In Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV) (eds. Agapito, L., Berg, T., Kosecka, J., & Zelnik-Manor, L.) pp. 6675–6683 (IEEE, Paris, FR, 2024).
16. Canny, J. A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 8, 679–698 (1986).10.1109/TPAMI.1986.4767851 ↗
17. Kanopoulos, N., Vasanthavada, N. & Baker, R. L. Design of an image edge detection filter using the sobel operator. IEEE J. Solid-state Circuits 23, 358–367 (1988).10.1109/4.996 ↗
18. Xu, C., Su, J., Wang, T., Zhang, Y. & Yu, A. Improved Canny edge detection operator. In Proc. 2023 7th Int. Conf. Commun. Inf. Syst. (ICCIS) (ed. Zhang, Y.) pp. 135–140 (IEEE Comput. Soc., Chongqing, CN, 2023).10.1109/ICCIS59958.2023.10453881 ↗
19. Zhang, C. & Fang, J. D. Edge detection based on improved Sobel operator. In Proc. 2016 Int. Conf. Comput. Eng. Inf. Syst. (CEIS) (ed. Zhang, Y.) pp. 129–132 (Atlantis Press, Shanghai, CN, 2016).10.2991/ceis-16.2016.25 ↗
20. Zangana, H. M., Mohammed, A. K. & Mustafa, F. M. Advancements in edge detection techniques for image enhancement: a comprehensive review. Int. J. Artif. Intell. Robot. 6, 29–39 (2024).10.25139/ijair.v6i1.8217 ↗
21. Ji, S., Yuan, X. & Bao, J. Efficient stage features for edge detection. In Proc. 2024 9th Int. Conf. Signal Image Process. (ICSIP) (eds Li, B., Chen, L.) pp. 628–632 (IEEE, Nanjing, CN, 2024).10.1109/ICSIP61881.2024.10671481 ↗
22. Jing, D., Li, B., Wang, S., Lin, J., & Jiao, Y. Edge detection in dark industrial environments. In Proc. 2023 Int. Conf. Comput. Commun. (ICCC) (eds. Ma, J., Guan, S., Ishibashi, Y.) pp. 1689–1693 (IEEE, Chengdu, CN, 2023).10.1109/ICCC59590.2023.10507668 ↗
23. Cui, S., Gui, Z., Hou, X., Peng, S., & Zhang, Q. Multi-scale generation and discrimination for sketch extraction of painted cultural relics. In Proc. 2023 2nd Int. Conf. Image Process. Media Comput. (ICIPMC) (eds. Ma, J., Guan, S., Ishibashi, Y.) pp. 95–100 (IEEE, Xi’an, CN, 2023).10.1109/ICIPMC58929.2023.00023 ↗
24. Luo, W., & Yang, K. Target detection method for edge computing based on the improved YOLOv5 algorithm. In Proc. 2024 4th Int. Conf. Electron. Circuits Inf. Eng. (ECIE) (eds. Ma, J., Guan, S., Ishibashi, Y.) pp. 640–644 (IEEE, Hangzhou, CN, 2024).10.1109/ECIE61885.2024.10627610 ↗
25. Makka, A., Pateraki, M., Betsas, T., & Georgopoulos, A. 3D edge detection based on normal vectors. In Proc. 2024 Int. Workshop 3D Virtual Reconstruct. Vis. Complex Archit. (3D-ARCH) (eds. Campana, S., Fassi, F., Remondino, F.) pp. 295–300 (ISPRS, Siena, IT, 2024).10.5194/isprs-archives-XLVIII-2-W4-2024-295-2024 ↗
26. Hu, J., & Fang, W. Intelligent clean line drawing. In Proc. 2016 Int. Conf. Robots Intell. Syst. (ICRIS) (eds. Ma, J., Guan, S., Ishibashi, Y.) pp. 217–220 (IEEE, Zhangjiajie, CN, 2016).10.1109/ICRIS.2016.44 ↗
27. Zhang, J., Wang, R.Z., & Xu, D. Automatic generation of sketch-like pencil drawing from image. In Proc. 2017 IEEE Int. Conf. Multimedia Expo Workshops (ICMEW) (eds. Ma, J., Guan, S., Ishibashi, Y.) pp. 261–266 (IEEE, Hong Kong, CN, 2017).10.1109/ICMEW.2017.8026301 ↗
28. Wang, T., Cao, C., Wang, C., Wang, Z. & Feng, Y. Coherence-enhancing line drawing for color images. Sci. China Inf. Sci. 56, 1–15 (2013).
29. Liu, J., Lu, D., & Shi, X. Interactive sketch generation for Dunhuang frescoes. In Proc. 2006 Int. Conf. Technol. E-Learn. Digit. Entertain. (Edutainment) (eds. Pan, Z., Aylett, R., Diener, H., Jin, X., Göbel, S., Li, L.) pp. 943–946 (Springer, Hangzhou, CN, 2006).10.1007/11736639_115 ↗
30. He, J., Wang, S., Zhang, Y., & Zhang, J. A computational fresco sketch generation framework. In Proc. 2013 IEEE Int. Conf. Multimedia Expo (ICME) (eds. Ma, J., Guan, S., Ishibashi, Y.) pp. 1–6 (IEEE, San Jose, CA, USA, 2013).10.1109/ICME.2013.6607509 ↗
31. Sun, D., Zhang, J., Pan, G., & Zhan, R. Mural2Sketch: A combined line drawing generation method for ancient mural painting. In Proc. 2018 IEEE Int. Conf. Multimedia Expo (ICME) (eds. Ma, J., Guan, S., Ishibashi, Y.) pp. 1–6 (IEEE, San Diego, CA, USA, 2018).10.1109/ICME.2018.8486504 ↗
32. Huang, Z., Peng, Y., Xie, H., Fukusato, T., & Miyata, K. One-shot line extraction from color illustrations. In Proc. 2021 Nicograph Int. (NicoInt) (eds. Ma, J., Guan, S., Ishibashi, Y.) pp. 19–22 (IEEE, Virtual Conf., 2021).10.1109/NICOINT52941.2021.00011 ↗
33. Lee, G. et al. Unpaired sketch-to-line translation via synthesis of sketches. In Proc. SIGGRAPH Asia 2019 Tech. Briefs (eds. Ma, J., Guan, S., Ishibashi, Y.) pp. 45–48 (ACM, Brisbane, AU, 2019).10.1145/3355088.3365163 ↗
34. Zhang, Q. et al. Deep learning for the extraction of sketches from spectral images of historical paintings. In Proc. SPIE 11784, Optics for Arts, Architecture, and Archaeology VIII (eds. Liang, H., & Groves, R.) pp. 11–20 (SPIE, Washington, DC, USA, 2021).10.1117/12.2593680 ↗
35. Xu, P. et al. Deep learning for free-hand sketch: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 45, 285–312 (2023).10.1109/TPAMI.2022.3148853 ↗
36. Deng, Y. & Liu, Y. Deep structural contour detection. ACM Trans. Multimed. Comput., Commun., Appl. ((TOMM)) 16, 1–19 (2020).10.1145/3369393 ↗
37. Wang, N., Wang, W. & Hu, W. Thangka mural line drawing based on cross dense residual architecture and hard pixel balancing. IEEE Access 9, 48841–48850 (2021).10.1109/ACCESS.2021.3068199 ↗
38. Wang, J., Liu, B., Li, J., Liu, W. & Du, S. Multi-stage feature fusion network for edge detection of Dunhuang murals. In Proc. 2023 35th Chin. Control Decis. Conf. (CCDC) (eds. Zhang, J. F., Wang, F., & Ma, H.) pp. 4684–4689 (IEEE, Yichang, CN, 2023).10.1109/CCDC58219.2023.10327241 ↗
39. Liu, B., He, F., Du, S., Zhang, K. & Wang, J. Dunhuang murals contour generation network based on convolution and self-attention fusion. Appl. Intell. 53, 22073–22085 (2023).10.1007/s10489-023-04614-4 ↗
40. Peng, J. et al. A relic sketch extraction framework based on detail-aware hierarchical deep network. Signal Process. 183, 108008 (2021).10.1016/j.sigpro.2021.108008 ↗
41. Yu, Z., Lyu, S., Hou, M., Sun, Y. & Li, L. A new method for extracting refined sketches of ancient murals. Sensors 24, 2213 (2024).10.3390/s24072213 ↗
42. Zhang, X. The Dunhuang caves: showcasing the artistic development and social interactions of Chinese Buddhism between the 4th and the 14th centuries. J. Educ. Humanit. Soc. Sci. 21, 266–279 (2023).
43. Jin, J. & Sharudin, S. A. B. A Study on the Influence of the 8th Century A.D. Image of Feitian in the Mogao Caves on the character design of modern Chinese films. Art. Soc. 2, 76–80 (2023).10.56397/AS.2023.12.10 ↗
44. Li, L. et al. Line drawing guided progressive inpainting of mural damage. arXiv Preprint:2211.06649 (2022).
45. Kilic, U. et al. Exploring the effect of image enhancement techniques with deep neural networks on direct urinary system x-ray (dusx) images for automated kidney stone detection. Int. J. Intell. Syst. 2023, 3801485 (2023).10.1155/2023/3801485 ↗
46. Liu, C. et al. The Medical image denoising method based on the CycleGAN and the complex shearlet transform. Int. J. Adv. Comput. Sci. Appl. 14, 118−125 (2023).10.14569/IJACSA.2023.0140814 ↗
47. Pu, M., Huang, Y., Liu, Y., Guan, Q. & Ling, H. Edter: Edge detection with transformer. In Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR) (eds. Agapito, L., Berg, T., Kosecka, J., & Zelnik-Manor, L.) pp. 1402–1412 (IEEE, New Orleans, LA, USA, 2022).10.1109/CVPR52688.2022.00146 ↗
48. Liu, Z. Searching for a lost aura: a Naxi Dongba’s spatial practices and space remaking in touristic commoditization. J. Tour. Cult. Change 16, 348–364 (2018).10.1080/14766825.2017.1332069 ↗
49. Yang, L., & Yu, Y. Restoration algorithm of Lijiang Baisha murals based on structure tensor and gradient priority calculation. In Proc. 2023 2nd Int. Conf. Big Data, Inf. Comput. Netw. (BDICN) (eds. Ma, J., Guan, S., & Ishibashi, Y.) pp. 305–311 (IEEE, Xishuangbanna, CN, 2023).10.1109/BDICN58493.2023.00070 ↗
50. Silva, A. G. & Lotufo, R.d.A. Detection of lines using hierarchical region based representation. In Proc. 17th Brazilian Symp. Comput. Graph. Image Process. (SIBGRAPI) (eds. Silva, F. G. M., & Gomes, A. J. P.) pp. 58–64 (IEEE Comput. Soc., Curitiba, BR, 2004).10.1109/SIBGRA.2004.1352943 ↗
51. Haralick, R. M., Shanmugam, K. & Dinstein, I. H. Textural features for image classification. IEEE Trans. Syst. Man Cybern. 6, 610–621 (2007).
52. Zhou Wang, U., Bovik, A. C., Sheikh, H. R. & Simoncelli, E. P. Image quality assessment: From error visibility to structural similarity. IEEE Trans. Image Process. 13, 600–612 (2004).10.1109/TIP.2003.819861 ↗
53. Buades, A., Coll, B. & Morel, J.-M. A non-local algorithm for image denoising. In Proc. 2005 IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. (CVPR) (eds. Schmid, C., Soatto, S., & Tomasi, C.) pp. 60–65 (IEEE Comput. Soc., San Diego, CA, USA, 2005).10.1109/CVPR.2005.38 ↗
54. Metri, S. & Asha, T. Patch based wiener filter for image denoising. In Proc. 2018 Int. Conf. Comput. Tech., Electron. Mech. Syst. (CTEMS) (eds. Deshpande, S., & Kenchannavar, H.) pp. 392–396 (IEEE, Belagavi, IN, 2018).10.1109/CTEMS.2018.8769307 ↗
55. Henry, J., Natalie, T. & Madsen, D. Pix2Pix GAN for image-to-image translation. In Proc. 2021 Int. Conf. Comput. Vis. Appl. (ICVA) (eds. Smith, A., & Johnson, B.) pp. 1–5 (ResearchGate, Virtual Conf., 2021).