The digital conservation of cultural clothing relics plays a pivotal role in restoring damaged textile textures, patterns, and structures within precious cultural heritage. Our work systematically reviewed studies from the past decade, examining the defined four-stage workflow (image acquisition/preprocessing, damage restoration, 3D modeling, virtual presentation), categorizing restoration methods across three dimensions: texture repair (sample completion, multilayer dictionary-variational autoencoder method, Poisson equation-based method), pattern restoration (structure-guided method, color clustering method), and structural reconstruction (deep learning-based methods, feature extraction-clustering method), with core techniques demonstrating enhanced edge restoration, structural coherence, and fragment reassembly as validated through integrated evaluation systems. These approaches have demonstrated significant efficacy in enhancing restoration outcomes. By analyzing technical challenges in practical scenarios, this study clarified targeted solutions for addressing diverse types of damage such as fractures, fading, and structural collapse, proposing a hierarchical restoration framework. Future research should prioritize precision restoration of damaged areas and explore integrated models for visualization and cultural revitalization.
ZhaoDXuLChenL, et al. Mask-Pix2Pix network for overexposure region recovery of solar image. Adv Astron2019; 2019: 1–10.
4.
DongJYinRSunX, et al. Inpainting of remote sensing SST images with deep convolutional generative adversarial network. IEEE Geosci Remote Sens Lett2019; 16: 1–5.
5.
QuanWChenJLiuY, et al. Deep learning-based image and video inpainting: A survey. Int J Comput Vision 2024; 132: 2367–2400.
6.
XuZZhangXChenW, et al. A review of image inpainting methods based on deep learning. Appl Sci2023; 13: 11189.
7.
Barrientos RojasDJFernandesBJTFernandesSMM.A review on image inpainting techniques and datasets. 2020 33rd SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), Porto de Galinhas, Brazil. 2020; 240-247. IEEE.
8.
GoodfellowIJPouget-AbadieJMirzaM, et al. Generative adversarial nets. Adv Neural Inf Process Syst2014; 27: 2672–2680.
9.
LiuSZhaoHYangT, et al. Analytical methods for materials and dyes of textile cultural relics. Sci Conserv Archaeol2021; 33(2): 110–119.
10.
WeiYWanZSuZ, et al. Study on the aging mechanism of textile relics in museum collection environment by accelerated aging experiment. J Nat Fibers2024; 21(1): 2296912.
11.
WangS.Application of chemical restoration technology of archaeological relics in the field of cultural relics protection. Plastics Industry2020; 48(11): 187–188.
12.
GeminianiLCampioneFPCortiC, et al. Historical silks: A novel method to evaluate their condition with ATR-FTIR spectroscopy and principal component analysis. J Cult Herit2024; 67: 9-22.
13.
ZhangYRenL.The construction of archives restoration resource sharing platform under the strategy of cultural digitization: Value, framework and guarantee. Arch Sci Bull2023; (6): 14–23.
14.
DingQLiangH.Digital restoration and reconstruction of heritage clothing: A review. Herit Sci2024; 12: 225.
15.
DuHDengYLvL, et al. On-site rapid detection of ancient leather using a dual recognition strategy. Anal Methods2025; 17: 2978-2986.
16.
ZhaoFWangSWangL.Research on silk unearthed in B121 cave in the north area of Mogao Grottoes. Dunhuang Res2021; (4): 4–16.
17.
GigilashviliDNguyenHTGulbrandsenCF, et al. Texture-based clustering of archaeological textile images. Archiv Conf2023; 20(1): 139–142.
18.
LiuXWangRXuQ.Restoration of 3D virtual fitting structure of women’s clothing in Tang Zhaoling mural. J Silk2022; 59(2): 87–93.
19.
LiangH.Advances in multispectral and hyperspectral imaging for archaeology and art conservation. Appl Phys A2022; 106: 309–323.
20.
YahaghiEGarcíaJAMMovafeghiA, et al. Improving X-ray images of historically significant textiles. J Cult Herit2024; 66: 415–425.
21.
Kodrič KesoviaMMMPenavaŽJemoD.The story of two historical textile fragments: Technical analysis and reconstruction of the lost textile pattern. Text Res J2021; 91(23-24): 2859–2871.
22.
ChengHLiangJLiuH.Image restoration fabric defect detection based on the dual generative adversarial network patch model. Text Res J2023; 93(11-12): 2859–2876.
23.
StoeanCBacaninNStoeanR, et al. On using perceptual loss within the U-Net architecture for the semantic inpainting of textile artefacts with traditional motifs. In Proceedings of the 24th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, Hagenberg/Linz, Austria, 2022, pp.276–283. IEEE.
24.
DuY.Research on fabric drape simulation based on Maya 3D technology. Master’s Thesis, Beijing Institute of Fashion Technology2017.
25.
LvZXieQZhuS, et al. OpenGL import 3DS model simulation clothing try-on. J Xi’an Polytech Univ2014; 28(4): 440–444.
26.
LiuKWuHJiY, et al. Archaeology and restoration of costumes in Tang tomb murals based on reverse engineering and human-computer interaction technology. Sustain2022; 14(10): 6232.
27.
IslamTMironALiuX, et al. StyleVTON: A multi-pose virtual try-on with identity and clothing detail preservation. Neurocomputing2024; 594: 127887.
28.
WanYFuY.Application of augmented reality technology in the field of clothing. Wool Spin Sci Techn2018; 46(5): 57–61.
29.
RuiKHeJ.Application progress of motion capture system in the clothing field. Shanghai Text Sci Tech2021; 49(6): 5–12.
30.
JiangCWangJYuL.Research on digital restoration method of textile cultural relic patterns. J Silk2019; 56(11): 21–25.
31.
GuiYZouXXiaoS, et al. An improved digital image restoration method based on texture synthesis. Comput Digital Eng2015; 43(9): 1651–1654.
32.
HouYPengJHanD.Research on improved Criminisi image restoration algorithm. Comput Eng Appl2015; 51(11): 135–144.
33.
ChenDZhangWJZhangWRWangXKWangHMLuoWG. A miniature world: Revealing warring states period shell paintings from zhongshan state by multiple-methods. J Cult Herit2024; 67: 461–469.
34.
PérezPGangnetMBlakeA.Poisson image editing. ACM Trans Graph2003; 22: 313–318.
35.
TangHGengGZhouM.Application of digital processing in relic image restoration design. Sens Imaging2020; 21(1): 6.
36.
ZhuYLiZWuT.Image restoration for regular ancient fabric texture. Cott Text Technol2017; 45(10): 9–12.
37.
XingBShaoQZengX, et al. Fabric texture reconstruction via multilayer dictionary learning. In Proceedings of the Second International Conference of Innovative Textiles and Developed Materials-ITDM’2; 05-06 May 2023, Tunisia. ITDM 2023. Springer, Singapore, 2023: pp.267–274.
38.
WangWDengNXinB, et al. Research on texture image inpainting of jacquard fabric based on non-single vision. Text Res J2020; 90: 13–14.
39.
ShaoHWangYFuY, et al. Generative image inpainting via edge structure and color aware fusion. Signal Process Image Commun2020; 87: 115929.
40.
LiNQiWJiaoJ, et al. SPCC: A superpixel and color clustering based camouflage assessment. Multim Tools Appl2024; 83: 26255-26279.
41.
YuJLinZYangJ, et al. Generative image inpainting with contextual attention. In Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018, pp.5505–5514. IEEE.
42.
ZhangJXinBYuanZ, et al. Digital restoration method of textile patterns based on edge guidance. J Text Res2024; 45(2): 101–111.
43.
SunXJiaTXuP, et al. Virtual restoration of defective silk cultural relics based on structure line fitting. J Silk2023; 60(1): 1–8.
44.
ZhaoCMiCTangB, et al. Study on the restoration and application of damaged textile cultural relics of ethnic minorities in western Hunan. In Proceedings of the 3rd International Conference on Electronic Information Technology and Smart Agriculture. Sanya, China: ACM, 2023, pp.472–476.
45.
LiQLiLWangW, et al. Image restoration of damaged textile cultural relics based on improved Criminisi algorithm. Prog Laser Optoelectron2023; 60(16): 173–182.
46.
ShaSLiYWeiW, et al. Image classification and restoration of ancient textiles based on convolutional neural network. Int J Comput Intell Syst2024; 17(1): 11.
47.
ShaSWeiWLiQ, et al. Image restoration of tomb textiles of Chu State based on deep learning. J Silk2023; 60(5): 1–7.
48.
GigilashviliDLukesovaHGulbrandsenCF, et al. Computational techniques for virtual reconstruction of fragmented archaeological textiles. Herit Sci2023; 11(1): 259.
49.
JaidilertSFarooqueG.Crack detection and images inpainting method for Thai mural painting images. In Proceedings of the 2018 IEEE 3rd International Conference on Image, Vision and Computing, Chongqing, China, 2018: pp.143–148. IEEE.
50.
WangHLiQJiaS.A global and local feature weighted method for ancient murals inpainting. Int J Mach Learn Cybern2020; 11(6): 1197–1216.
51.
WangHLiQZouQ.Inpainting of Dunhuang murals by sparsely modeling the texture similarity and structure continuity. J Comput Cult Her2019; 12(3): 1–21.
52.
LiLZouQZhangF, et al. Line drawing guided progressive inpainting of mural damage. J Comput Cult Herit2025; 18(3): 48.
53.
CaoJZhangZZhaoA, et al. Ancient mural restoration based on a modified generative adversarial network. Herit Sci 2020; 8: 7.
54.
DengXYuY.Ancient mural inpainting via structure information guided two-branch model. Herit Sci2023; 11(1): 131.
55.
GeHYuYZhangL.A virtual restoration network of ancient murals via global–local feature extraction and structural information guidance. Herit Sci2023; 11(1): 264.
56.
StoeanCBacaninNStoeanR, et al. On using perceptual loss within the U-net architecture for the semantic inpainting of textile artefacts with traditional motifs. In Proceedings of the 24th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing. Hagenberg / Linz, Austria: IEEE, 2022, pp.276–283.
57.
LvCLiZShenY, et al. SeparaFill: Two generators connected mural image restoration based on generative adversarial network with skip connect. Herit Sci2022; 10(1): 135.
58.
GulbrandsenCF. Reconstructing the original: Machine learning puzzle assembly for matching archaeological textile fragments. Master’s Thesis, Norges teknisk-naturvitenskapelige universitet, 2023.
59.
XiaoPQiuPJHaSMBaniAZhouSSotirasA, et al. SC-VAE: Sparse coding-based variational autoencoder with learned ISTA. Pattern Recogn 2025; 161: 111187.
60.
WangY.Research on the design of cultural and creative products of Shanghai-style watercolor painting based on style transfer algorithm. Master’s Thesis, East China University of Science and Technology, 2020.
61.
LiYGaoYYanJ, et al. Review of image inpainting methods based on deep neural networks. Chin J Comput2021; 44(11): 2295–2316.
62.
BakurovIBuzzelliMSchettiniR, et al. Structural similarity index (SSIM) revisited: A data-driven approach. Expert Syst Appl2022; 189: 116087.
63.
KorhonenJYouJ.Peak signal-to-noise ratio revisited: Is simple beautiful? In Proceedings of the 2012 Fourth International Workshop on Quality of Multimedia Experience, Melbourne, VIC, Australia, 2012, pp.37–38. IEEE.
64.
López-FernándezLGarcíaBGallegoM, et al. Designing and evaluating the usability of an API for real-time multimedia services in the Internet. Multim Tools Appl2017; 76(12): 14247–14304.
65.
HeuselMRamsauerHUnterthinerT, et al. GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS’17). Curran Associates Inc., Red Hook, NY, USA, pp. 6629–6640.
66.
HeKChenXXieS, et al. Masked autoencoders are scalable vision learners. In Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 2022, pp.15979–15988.
67.
MaLHeSLuM.A measurement of visual complexity for heterogeneity in the built environment based on fractal dimension and its application in two gardens. Fractal Fract2021; 5(4): 278.
68.
NollAM.Human or machine: A subjective comparison of Piet Mondrian’s “Composition with Lines” (1917) and a computer-generated picture. Psychol Rec1966; 16(1): 1–10.
