High Resolution Image Generation Algorithm for Archaeology Drawings

Authors: X. Zeng, L. Cheng, Z. Li, X. Liu

Abstract:

Aiming at the problem of low accuracy and susceptibility to cultural relic diseases in the generation of high-resolution archaeology drawings by current image generation algorithms, an archaeology drawings generation algorithm based on a conditional generative adversarial network is proposed in this paper. An attention mechanism is added into the high-resolution image generation network as the backbone network, which enhances the line feature extraction capability and improves the accuracy of line drawing generation. A dual-branch parallel architecture consisting of two backbone networks is implemented, where the semantic translation branch extracts semantic features from orthophotographs of cultural relics, and the gradient screening branch extracts effective gradient features. Finally, the fusion fine-tuning module combines these two types of features to achieve the generation of high-quality and high-resolution archaeology drawings. Experimental results on the self-constructed archaeology drawings dataset of grotto temple statues show that the proposed algorithm outperforms current mainstream image generation algorithms in terms of pixel accuracy (PA), structural similarity (SSIM), and peak signal-to-noise ratio (PSNR) and can be used to assist in drawing archaeology drawings.

Keywords: Archaeology drawings, digital heritage, image generation, deep learning.

References:

[1] Ma H Z. Field Archaeological Mapping (M). Beijing: Peking University Press, 2010: 10-14.
[2] Ma H Z. Drawing of Archaeological Artifacts (M). Beijing: Peking University Press, 2008: 1-4.
[3] Li X F. Research and Implementation of Line Graph Generation and Measurement Method of 3D Model of Cultural Relic (D). Northwest University, 2013.
[4] Wang X, Geng G, Li X, et al. A cultural relic line drawings generation algorithm based on explicit ridge line,2015 International Conference on Virtual Reality and Visualization (ICVRV),2015.
[5] Liu F J. Generation and Rendering of Non-photorealistic Line Graph based on Two-dimensional Images (D). Northwest University, 2013.
[6] Song Q N. Research and implementation of Cultural Relics Line Drawing method based on Cellular Ant Colony Edge Extraction (D). Northwest University, 2019.
[7] LeCun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition (J). Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[8] Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial networks (J). Communications of the ACM, 2020, 63(11): 139-144.
[9] Mirza, S Osindero. Conditional Generative Adversarial Nets 2014. arXiv preprint 2014 (J), arXiv:1411.1784.
[10] Isola P, Zhu J Y, Zhou T, et al. Image-to-image translation with conditional adversarial networks (C)//Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). 2017: 1125-1134.
[11] Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation (C)//Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. Springer International Publishing, 2015: 234-241.
[12] Peng J, Wang J, Wang J, et al. A relic sketch extraction framework based on detail-aware hierarchical deep network. Signal Processing, 2021, Vol.183.
[13] He J, Zhang S, Yang M, et al. Bi-directional cascade network for perceptual edge detection (C)//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2019: 3828-3837.
[14] Wang T C, Liu M Y, Zhu J Y, et al. High-resolution image synthesis and semantic manipulation with conditional GANs (C)//Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). 2018: 8798-8807.
[15] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition (J). International Conference on Learning Representations, 2015: 1-14.
[16] Woo S, Park J, Lee J Y, et al. Cbam: Convolutional block attention module (C)//Proceedings of the European conference on computer vision. 2018: 3-19.
[17] Rumelhart D E, Hinton G E, Williams R J. Learning representations by back-propagating errors (J). nature, 1986, 323(6088): 533-536.
[18] Zhang Z, Wang H, Zhao K Y. Yungang Grottoes: Volume I (M). Shandong: Qingdao Publishing House, 2017: 1-331.
[19] Mizuno S, Nagahiro T. Yun-Kang: the Buddhist cave-temples of the fifth century A.D. in North China: Detailed report of the archaeological survey carried out by the Mission of the Tōhōbunka kenkyūsho 1938-45. Volume X Caves Thirteen and Outside Wall of Caves XI-XIII (M). Kyoto: Kyoto University Yungang Press, 1953: 1-45.
[20] Ningxia Institute of Cultural Relics and Archaeology, Zhejiang University Cultural Heritage Institute, Xumu Mountain Grottoes Cultural Relics Management Institute. Archaeological Report of Xumishan Grottoes: Yuanguangsi District (M). Beijing: Cultural Relics Press, 2020: 1-130.
[21] Kingma D P, Ba J. Adam: A method for stochastic optimization (J). arXiv preprint 2014. arXiv:1412.6980.