The existing deep learning methods don’t make full use of the prior information such as semantic and texture information in intact area of mural restoration, which results in poor restoration results, so a mural restoration algorithm based on semantic prior and texture enhancement guidance is proposed. Firstly, a semantic prior learning module is designed, which maps the original mural semantic features to a semantic prior learner through pixel folding operations. The original semantic features are used to guide the repair of incomplete features, gradually reducing the difference between damaged and original semantic features. Then, a texture enhancement module is designed, which enhances texture details by fusing contextual information modules and fusing them to complete the restoration of mural texture features. Finally, an aggregate bootstrap module is designed, which integrates the semantic prior repair and texture enhancement results, decodes them to the original resolution, and completes the repair of damaged murals through adversarial games with Markov discriminators. The digital classification restoration experiment of Dunhuang murals shows that the proposed method outperforms the comparative algorithm in both subjective and objective evaluations, achieving better restoration results.
FUX Y, LIY, SUNZ J,et al .Digital color restoration of soot covered murals in the Mogao Grottoes at Dunhuang[J]. Dunhuang Research, 2021(1): 137-147.(in Chinese)
[5]
SHUMBHAMK W, SHREYAR H, SNEHAS T, et al. Image inpainting using total variation algorithm[J]. International Journal of Innovative Research in Engineering,2022,3(3):101-105.
[6]
LIUH S, CAOS T, LINGY Y,et al .Inpainting for saturation artifacts in optical coherence tomography using dictionary-based sparse representation[J].IEEE Photonics Journal,2021,13(2):3900110.
[7]
YANGT, ZHAOJ H. An improved method of CRIMINISI algorithm[C]//2021 3rd International Conference on Advances in Computer Technology,Information Science and Communication (CTISC). Shanghai, China. IEEE,2021:367-371.
[8]
WANGH, LIQ Q, JIAS .A global and local feature weighted method for ancient murals inpainting[J].International Journal of Machine Learning and Cybernetics,2020,11(6):1197-1216.
CHENY, AIY P, GUOH G .Inpainting algorithm for Dunhuang mural based on improved curvature-driven diffusion model[J].Journal of Computer-Aided Design & Computer Graphics,2020,32(5):787-796.(in Chinese)
LIL, GAOR W, MEIS L,et al .Mural image de-noising based on Shannon-Cosine wavelet precise integration method[J].Journal of Zhejiang University (Science Edition),2019, 46(3):279-287.(in Chinese)
WANGH, LIL, LIQ, et al. A global uniform and local continuity repair method for murals inpainting[J]. Journal of Hunan University (Natural Sciences), 2022, 49(6): 135-145.(in Chinese)
CHENY, ZHAOM X, TAOM F .Mural inpainting algorithm for group sparse based on multi-scale contourlet transform decomposition[J]. Journal of Xidian University,2022,49(6):120-128.(in Chinese)
[21]
QINJ, BAIH H, ZHAOY .Multi-scale attention network for image inpainting[J].Computer Vision and Image Understanding,2021,204:103155.
[22]
IIZUKAS, SIMO-SERRAE, ISHIKAWAH .Globally and locally consistent image completion[J].ACM Transactions on Graphics,2017,36(4): 1-14.
ZHAOL, LINS H, LINZ J,et al .Progressive multilevel feature inpainting algorithm for Chinese ancient paintings[J].Journal of Computer-Aided Design & Computer Graphics,2023,35(7):1040-1051.(in Chinese)
WENL L, XUD, ZHANGX,et al .The inpainting of irregular damaged areas in ancient murals using generative model[J].Journal of Graphics,2019,40(5): 925-931.(in Chinese)
[30]
WADHWAG, DHALLA, MURALAS,et al .Hyperrealistic image inpainting with hypergraphs[C]//2021 IEEE Winter Conference on Applications of Computer Vision (WACV). Waikoloa,HI,USA. IEEE, 2021: 3911-3920.
[31]
GUOZ Y, CHENZ B, YUT,et al .Progressive image inpainting with full-resolution residual network[C]//Proceedings of the 27th ACM International Conference on Multimedia. Nice, France. ACM, 2019: 85-100.
[32]
LIJ Y, WANGN, ZHANGL F,et al .Recurrent feature reasoning for image inpainting[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle,WA,USA. IEEE, 2020: 7757-7765.
[33]
LIX G, GUOQ, LIND,et al .MISF:multi-level interactive Siamese filtering for high-fidelity image inpainting[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans, LA,USA. IEEE, 2022: 1859-1868.
CHENY, ZHAOM X, TAOM F .Progressive mural inpainting method based on joint feature reasoning and semantic enhancement[J]. Journal of Hunan University (Natural Sciences), 2023, 50(8): 1-12.(in Chinese)
LIUZ M, YANL. Inpainting model of Dunhuang mural fusing dynamic feature and attention[J]. Computer Engineering, 2024,50(5): 342-353.(in Chinese)
[38]
NAZERIK,NG E, JOSEPHT,et al. EdgeConnect:structure guided image inpainting using edge prediction[C]//2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). Seoul, Korea (South). IEEE, 2019: 3265-3274.
[39]
LIJ Y, HEF X, ZHANGL F,et al .Progressive reconstruction of visual structure for image inpainting[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul,Korea (South). IEEE, 2019: 5961-5970.
[40]
XIONGW, YUJ H, LINZ,et al .Foreground-aware image inpainting[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach,CA,USA. IEEE,2019:5833-5841.
[41]
YUJ H, LINZ, YANGJ M,et al. Generative image inpainting with contextual attention[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City,UT,USA. IEEE, 2018: 5505-5514.
[42]
GUOQ, LIX G, JUEFEI-XUF, et al. JPGNet:joint predictive filtering and generative network for image inpainting[C]//Proceedings of the 29th ACM International Conference on Multimedia. Virtual Event China. ACM, 2021: 386-394.
HUK, ZHAOJ, LIUY,et al .Images inpainting via structure guidance[J].Journal of Beijing University of Aeronautics and Astronautics,2022,48(7):1269-1277.(in Chinese)
[45]
GUOX F, YANGH Y, HUANGD. Image inpainting via conditional texture and structure dual generation[C]//2021 IEEE/CVF International Conference on Computer Vision (ICCV). Montreal,QC,Canada. IEEE,2021:14114-14123.
[46]
HEJ, ZHOUY Y, ZHANGQ, et al. PixelFolder: an efficient progressive pixel synthesis network for image generation[M]//Computer Vision-ECCV 2022. Cham:Springer Nature Switzer- land, 2022: 643-660.
[47]
PARKT, LIUM Y, WANGT C,et al .Semantic image synthesis with spatially-adaptive normalization[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, CA, USA. IEEE, 2019: 2332-2341.
基金资助
教育部人文社会科学研究青年基金资助项目(19YJC760012)
Humanities and Social Sciences YouthFoundation of Ministry of Education(19YJC760012)
兰州交通大学基础研究拔尖人才项目(2023JC36)
Basic Top-notch Personnel Project of Lanzhou Jiaotong University(2023JC36)
兰州交通大学重点研发项目资助(ZDYF2304)
Key Research and Development Project of Lanzhou Jiaotong University(ZDYF2304)