AIGC多模态知识驱动的文化遗产图像修复发展现状

王伶羽; 方明珠; 郭美星; 胡舒娟; 胡洁; 梁爽; 闫雨; 黎映川

doi:10.19554/j.cnki.1001-3563.2026.04.001

PDF(10543 KB)

包装工程（设计栏目） ›› 2026, Vol. 47 ›› Issue (4) : 1-18. DOI: 10.19554/j.cnki.1001-3563.2026.04.001

工业设计

AIGC多模态知识驱动的文化遗产图像修复发展现状

王伶羽^1,2, 方明珠², 郭美星², 胡舒娟¹, 胡洁², 梁爽³, 闫雨³, 黎映川^4,*

作者信息 +

Development Status of Cultural Heritage Image Restoration Driven by AIGC Multi-modal Knowledge

WANG Lingyu^1,2, FANG Mingzhu², GUO Meixing², HU Shujuan¹, HU Jie², LIANG Shuang³, YAN Yu³, LI Yingchuan^4,*

Author information +

文章历史 +

摘要

目的旨在探讨生成式人工智能驱动的多模态知识库如何为传统文化遗产图像修复提供新的解决方案,推动文化遗产保护朝着智能化方向发展,以解决修复过程中存在的风格不一致与语义不连贯的问题。方法梳理AIGC技术从生成对抗网络到扩散模型的演变过程,着重分析多模态知识库的构建方式、知识调取与融合机制以及知识引导的可控生成机制。结合有代表性的修复平台案例,评估其在文化遗产图像修复中的应用成效。结果 AIGC驱动的多模态方法可有效整合图像、文本等多源数据,提升修复过程中的风格一致性与语义连贯性,在处理复杂损伤以及保持文化语境方面,比传统修复技术更具优势。结论 AIGC与多模态知识的融合为文化遗产图像修复开创了新的模式,推动了修复技术朝着智能化与系统化方向发展。未来平台化系统集成、深层语义对齐与可信保障、人机协同伦理规范构建将是发展的关键方向。

Abstract

The work aims to explore how multi-modal knowledge bases driven by AI Generated Content (AIGC) provide novel solutions for traditional cultural heritage image restoration and propel cultural heritage protection toward intelligent development, specifically addressing the challenges of stylistic inconsistency and semantic incoherence often encountered in the restoration process. By reviewing the evolution of AIGC technologies, from Generative Adversarial Networks (GANs) to diffusion models, the construction methods of multi-modal knowledge bases, the mechanisms of knowledge retrieval and fusion, and the controllable generation mechanisms guided by knowledge were analyzed. Representative restoration platform cases were also evaluated to assess their effectiveness in cultural heritage image restoration. The AIGC-driven multi-modal approach effectively integrated multi-source data such as images and text, significantly improving stylistic consistency and semantic coherence in the restoration process. It outperformed traditional restoration techniques in handling complex damage and maintaining cultural context. The integration of AIGC and multi-modal knowledge opens up a new paradigm for cultural heritage image restoration, driving the intelligent and systematic development of restoration technologies. In the future, key directions for development will include platform system integration, deep semantic alignment and trust assurance, as well as the construction of human-machine collaboration ethical norms.

导出引用1

王伶羽, 方明珠, 郭美星, 胡舒娟, 胡洁, 梁爽, 闫雨, 黎映川. AIGC多模态知识驱动的文化遗产图像修复发展现状[J]. 包装工程. 2026, 47(4): 1-18 https://doi.org/10.19554/j.cnki.1001-3563.2026.04.001

WANG Lingyu, FANG Mingzhu, GUO Meixing, HU Shujuan, HU Jie, LIANG Shuang, YAN Yu, LI Yingchuan. Development Status of Cultural Heritage Image Restoration Driven by AIGC Multi-modal Knowledge[J]. Packaging Engineering. 2026, 47(4): 1-18 https://doi.org/10.19554/j.cnki.1001-3563.2026.04.001

中图分类号： TB472

参考文献

[1] SHEN J J.The Investigation of Artificial Intelligence in Cultural Relics Protection[J]. Science and Technology of Engineering, Chemistry and Environmental Protection, 2024, 1(9): 1-8.
[2] 张逸勤, 邓三鸿, 王凡铭, 等. 国家文化数字化战略下的数字人文学科研究: 发展趋势与演进逻辑[J]. 情报科学, 2025, 43(6): 181-192.
ZHANG Y Q, DENG S H, WANG F M, et al.Analysis of the Evolutionary Trends in Digital Humanities Research from the Policy Perspective in China[J]. Information Science, 2025, 43(6): 181-192.
[3] MANJUNATHA, SRIMANI P S, GUPTA M, et al. Advanced AI Techniques for Restoring Historical Documents and Photographs with Generative Adversarial and Diffusion Models for Cultural Heritage Preservation[C]// 2025 International Conference on Cognitive Computing in Engineering, Communications, Sciences and Biomedical Health Informatics (IC3ECSBHI). Greater Noida, India. IEEE, 2025: 735-740.
[4] CONG L.A Framework Study on the Application of AIGC Technology in the Digital Reconstruction of Cultural Heritage[J]. Applied Mathematics and Nonlinear Sciences, 2024, 9: 20242190.
[5] HUNT B R.Prospects for Image Restoration[J]. International Journal of Modern Physics C, 1994, 5(1): 151-178.
[6] TANG H, GENG G H, ZHOU M Q.Application of Digital Processing in Relic Image Restoration Design[J]. Sensing and Imaging, 2019, 21(1): 6.
[7] AHMED H O, ALFAQHERI T, SADKA A H.Digital Image Inpainting Techniques for Cultural Heritage Preservation and Restoration[M]// Data Analytics for Cultural Heritage. Cham: Springer International Publishing, 2021: 91-122.
[8] WANG F.A Study of Digital Image Enhancement for Cultural Relic Restoration[J]. International Journal of Engineering and Technical Research (IJETR), 2017, 7(11): 41-44.
[9] JMAL M, SOUIDENE W, ATTIA R.Efficient Cultural Heritage Image Restoration with Nonuniform Illumination Enhancement[J]. Journal of Electronic Imaging, 2017, 26(1): 011020.
[10] GUI O.Aspects Regarding the Use of Image Processing for Tangible Cultural Heritage Conservation-Restoration[C]// 2017 International Conference on Optimization of Electrical and Electronic Equipment (OPTIM) & 2017 Intl Aegean Conference on Electrical Machines and Power Electronics (ACEMP). Brasov, Romania. IEEE, 2017: 833-838.
[11] LIU Z H.Literature Review on Image Restoration[J]. Journal of Physics: Conference Series, 2022, 2386(1): 012041.
[12] XU Z S, ZHANG X F, CHEN W, et al.A Review of Image Inpainting Methods Based on Deep Learning[J]. Applied Sciences, 2023, 13(20): 11189.
[13] ZOU Q.An Image Inpainting Model Based on the Mixture of Perona-Malik Equation and Cahn-Hilliard Equation[J]. Journal of Applied Mathematics and Computing, 2021, 66(1): 21-38.
[14] BUZATU O L, GORAS B T, GORAS L, et al.Image Analysis Techniques for Cultural Heritage Restoration Methods Evaluation[C]// 2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO). Bucharest, Romania. IEEE, 2012: 2723-2727.
[15] CHAN T F, SHEN J H.Nontexture Inpainting by Curvature-Driven Diffusions[J]. Journal of Visual Communication and Image Representation, 2001, 12(4): 436-449.
[16] 刘涵啸. 基于生成式网络的图像修复算法研究[D]. 西宁: 青海师范大学, 2025.
LIU H X.Research on Image Restoration Algorithm Based on Generative Network[D]. Xining: Qinghai Normal University, 2025.
[17] LECUN Y, BOSER B, DENKER J S, et al.Backpropagation Applied to Handwritten Zip Code Recognition[J]. Neural Computation, 1989, 1(4): 541-551.
[18] KINGMA D P, WELLING M. Auto-Encoding Variational Bayes[EB/OL].2013: arXiv: 1312.6114. https://arxiv.org/abs/1312.6114
[19] ULYANOV D, VEDALDI A, LEMPITSKY V.Deep Image Prior[J]. International Journal of Computer Vision, 2020, 128(7): 1867-1888.
[20] DUBOLAZOV O V, USHENKO O G, SOLTYS I V, et al.Researching the Possibilities of Using Ai Technologies for Digital Image Processing: Review and Applications[J]. Optoelectronic Information-Power Technologies, 2024, 48(2): 78-87.
[21] OLIVEIRA M M, BOWEN B, MCKENNA R, et al.Fast Digital Image Inpainting[C]// Proceedings of the International Conference on Visualization, Imaging and Image Processing (VIIP 2001). Marbella: 2001: 106-107.
[22] JAIN V, SEUNG S.Natural Image Denoising with Convolutional Networks[C]// Advances in Neural Information Processing Systems: Curran Associates, Inc., 2008.
[23] ZHENG C X, CHAM T J, CAI J F.Pluralistic Image Completion[C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach: IEEE, 2020: 1438-1447.
[24] HAN X T, WU Z X, HUANG W L, et al.FiNet: Compatible and Diverse Fashion Image Inpainting[C]// 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul: IEEE, 2020: 4480-4490.
[25] TU C T, CHEN Y F.Facial Image Inpainting with Variational Autoencoder[C]// 2019 2nd International Conference of Intelligent Robotic and Control Engineering (IRCE). Singapore: IEEE, 2020: 119-122.
[26] YEH R A, CHEN C, LIM T Y, et al.Semantic Image Inpainting with Deep Generative Models[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, USA. IEEE, 2017: 6882-6890.
[27] JBOOR N H, BELHI A, AL-ALI A K, et al. Towards an Inpainting Framework for Visual Cultural Heritage[C]// 2019 IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology (JEEIT). Amman: IEEE, 2019: 602-607.
[28] ELHARROUSS O, DAMSEH R, BELKACEM A N, et al.Transformer-Based Image and Video Inpainting: Current Challenges and Future Directions[J]. Artificial Intelligence Review, 2025, 58(4): 124.
[29] HUANG C H.INTJ: A Two-Stage Generative Adversarial Network for Cultural Image Restoration[C]// 2024 4th International Conference on Computer Communication and Artificial Intelligence (CCAI). Xi'an: IEEE, 2024: 87-93.
[30] ZHAO L, MO Q H, LIN S H, et al.UCTGAN: Diverse Image Inpainting Based on Unsupervised Cross-Space Translation[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, WA: IEEE, 2020: 5740-5749.
[31] CHEN Y T, LIU L W, TAO J J, et al.The Improved Image Inpainting Algorithm via Encoder and Similarity Constraint[J]. The Visual Computer, 2021, 37(7): 1691-1705.
[32] LI Y J, LIU S F, YANG J M, et al.Generative Face Completion[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE, 2017: 5892-5900.
[33] SUN Q R, MA L Q, JOON OH S, et al.Natural and Effective Obfuscation by Head Inpainting[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 5050-5059.
[34] DOLHANSKY B, FERRER C C.Eye In-Painting with Exemplar Generative Adversarial Networks[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 7902-7911.
[35] LIAO H F, FUNKA-LEA G, ZHENG Y F, et al.Face Completion with Semantic Knowledge and Collaborative Adversarial Learning[C]// Computer Vision-ACCV 2018. Cham: Springer, 2019: 382-397.
[36] ZHANG X, WANG X, SHI C H, et al.DE-GAN: Domain Embedded GAN for High Quality Face Image Inpainting[J]. Pattern Recognition, 2022, 124: 108415.
[37] GONG J, LUO S L, YU W X, et al.Structure-Guided Image Inpainting Based on Multi-Scale Attention Pyramid Network[J]. Applied Sciences, 2024, 14(18): 8325.
[38] HUANG R, ZHENG Y H.Image Structure-Induced Semantic Pyramid Network for Inpainting[J]. Applied Sciences, 2023, 13(13): 7812.
[39] FAN Q Q, WEI C, WU S Y, et al.Face Image Inpainting of Tang Dynasty Female Terracotta Figurines Based on an Improved Global and Local Consistency Image Completion Algorithm[J]. Applied Sciences, 2024, 14(24): 11621.
[40] N A D R, BABU B S, DANISH R, et al. Face Restoration of Ancient Indian Statues Using Image Inpainting[C]// 2025 Fourth International Conference on Smart Technologies, Communication and Robotics (STCR). Sathyamangalam: IEEE, 2025: 1-6.
[41] NING T, HUANG G W, LI J X, et al.Complex Image Inpainting of Cultural Relics Integrating Multi-Stage Structural Features and Spatial Textures[J]. Pattern Analysis and Applications, 2025, 28(2): 85.
[42] VASWANI A, SHAZEER N, PARMAR N, et al.Attention Is All You Need[C]// Advances in Neural Information Processing Systems: Curran Associates, Inc., 2017.
[43] MINEAULT P.Is Attention all You Need?[M]// From Human Attention to Computational Attention. Cham: Springer Nature Switzerland, 2025: 297-314.
[44] SHANG X P.Research on Lingnan Culture Image Restoration Methods Based on Multi-Scale Non-Local Self-Similar Learning[J]. IEEE Access, 2025, 13: 101639-101646.
[45] WANG T, XIANG D, YANG C, et al.NLKFill: High-Resolution Image Inpainting with a Novel Large Kernel Attention[J]. Complex & Intelligent Systems, 2024, 10(4): 4921-4938.
[46] YU X K, DAI L, CHEN Z H, et al.AGG: Attention-Based Gated Convolutional GAN with Prior Guidance for Image Inpainting[J]. Neural Computing and Applications, 2024, 36(20): 12589-12604.
[47] WAN Z Y, ZHANG J B, CHEN D D, et al.High-Fidelity Pluralistic Image Completion with Transformers[C]// 2021 IEEE/CVF International Conference on Computer Vision (ICCV): IEEE, 2022: 4672-4681.
[48] LIU T R, LIAO L, CHEN D L, et al.Transref: Multi-Scale Reference Embedding Transformer for Reference-Guided Image Inpainting[J]. Neurocomputing, 2025, 632: 129749.
[49] DHARIWAL P, NICHOL A.Diffusion Models Beat GANs on Image Synthesis[C]// Advances in Neural Information Processing Systems: Curran Associates, Inc., 2021: 8780-8794.
[50] LUGMAYR A, DANELLJAN M, ROMERO A, et al.RePaint: Inpainting Using Denoising Diffusion Probabilistic Models[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans: IEEE, 2022: 11461-11471.
[51] ROMBACH R, BLATTMANN A, LORENZ D, et al.High-Resolution Image Synthesis with Latent Diffusion Models[C]// 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans: IEEE, 2022: 10674-10685.
[52] 顾佐佐, 汪璐, 王玥. 人工智能驱动的非物质文化遗产智慧数据资源建设与共享机制[J]. 情报科学, 2025.
GU Z Z, WANG L, WANG Y.Construction and Sharing Mechanism of Intelligent Data Resources for Intangible Cultural Heritage Driven by Artificial Intelligence[J]. Information Science, 2025.
[53] 黄好阳, 李飞, 张恒郡, 等. 融合LLM与TLP的跨工艺文档多模态知识图谱建模方法[J]. 上海交通大学学报, 2025.
HUANG H Y, LI F, ZHANG H J, et al.Modeling Method of Multimodal Knowledge Graph for Cross-Process Documents Fusing LLM and TLP[J]. Journal of Shanghai Jiao Tong University, 2025.
[54] YUAN J, ZHANG J, WU F, et al.Towards Cross-Modal Retrieval in Chinese Cultural Heritage Documents: Dataset and Solution[C]// YIN X C, KARATZAS D, LOPRESTI D. Document Analysis and Recognition - ICDAR 2025. Cham: Springer Nature Switzerland, 2026: 570-586.
[55] JIANG L, MENG Z Q.Knowledge-Based Visual Question Answering Using Multi-Modal Semantic Graph[J]. Electronics, 2023, 12(6): 1390.
[56] WANG S, NAJDENKOSKA I, ZHU H Y, et al.ArtRAG: Retrieval-Augmented Generation with Structured Context for Visual Art Understanding[C]// Proceedings of the 33rd ACM International Conference on Multimedia. New York: NY, 2025: 6700-6709.
[57] XU Z S, ZHANG X F, YANG Y Q, et al.MuralAgent: Enhancing Ancient Mural Outpainting with RAG-Based Texts and Multimodal Integration[J]. ACM Transactions on Multimedia Computing, Communications, and Applications, 2025, 21(9): 1-17.
[58] RESHETNIKOV A, MARINESCU M C.Caption Generation in Cultural Heritage: Crowdsourced Data and Tuning Multimodal Large Language Models[C]// Proceedings of the 1st Workshop on Language Models for Underserved Communities (LM4UC 2025). Albuquerque: New MexicoAssociation for Computational Linguistics, 2025: 42-50.
[59] 位通, 张婷, 邓秋怡, 等. 大规模文化遗产图像数据化研究[J]. 中国图书馆学报, 2025, 51(2): 58-73.
WEI T, ZHANG T, DENG Q Y, et al.Datafication of Large-Scale Cultural Heritage Images[J]. Journal of Library Science in China, 2025, 51(2): 58-73.
[60] 仲会娟. 基于颜色特征和SVM的自然图像分类标注算法[J]. 绵阳师范学院学报, 2018, 37(5): 12-16.
ZHONG H J.Natural Image Automatic Annotation Algorithm Based on Color Feature and SVM[J]. Journal of Mianyang Teachers’ College, 2018, 37(5): 12-16.
[61] CARRIERO V A, GANGEMI A, MANCINELLI M L, et al.Pattern-Based Design Applied to Cultural Heritage Knowledge Graphs: ArCo: The Knowledge Graph of Italian Cultural Heritage[J]. Semantic Web: - Interoperability, Usability, Applicability, 2021, 12(2): 313-357.
[62] KALITA D, DEKA D P.Ontology for Preserving the Knowledge Base of Traditional Dances (OTD)[J]. The Electronic Library, 2020, 38(4): 785-803.
[63] WAN J, ZHANG H, ZOU J, et al.WuMKG: A Chinese Painting and Calligraphy Multimodal Knowledge Graph[J]. Heritage Science, 2024, 12: 159.
[64] WANG Y, LIU J, WANG W W, et al.Construction of Cultural Heritage Knowledge Graph Based on Graph Attention Neural Network[J]. Applied Sciences, 2024, 14(18): 8231.
[65] FAN T, WANG H, HODEL T.Multimodal Knowledge Graph Construction of Chinese Traditional Operas and Sentiment and Genre Recognition[J]. Journal of Cultural Heritage, 2023, 62: 32-44.
[66] 周正达, 王昊, 汪琳, 等. ChatKG:一种基于大语言模型和提示工程的非遗知识图谱构建框架——以中国非遗陶瓷制作工艺为例[J/OL]. 图书馆杂志, 1-30 [2025-02-24].https://link.cnki.net/urlid/31.1108.g2.20250224.1136.008.
ZHOU Z D, WANG H, WANG L, et al. ChatKG: A Construction Framework of Intangible Cultural Heritage Knowledge Graph Based on Large Language Model and Prompt Engineering—Taking Chinese Intangible Cultural Heritage Ceramic Production Process as an Example[J/OL]. Library Journal, 1-30 [2025-02-24]. https://link.cnki.net/urlid/31.1108.g2.20250224.1136.008.
[67] 陈涛, 张欣, 冯卓彤, 等. 文化遗产多模态资源知识统一表征模型构建研究[J]. 中国图书馆学报, 2025, 51(6): 60-77.
CHEN T, ZHANG X, FENG Z T, et al.Construction of Knowledge Unified Representation Model for Multimodal Resources of Cultural Heritage[J]. Journal of Library Science in China, 2025, 51(6): 60-77.
[68] 张云中, 李茜. 沪上名人故居知识图谱构建与应用研究[J]. 情报科学, 2023, 41(10): 1-11.
ZHANG Y Z, LI X.The Construction and Application of Knowledge Map of the Former Residences of Celebrities in Shanghai[J]. Information Science, 2023, 41(10): 1-11.
[69] BARZAGHI S, MORETTI A, HEIBI I, et al. CHAD-KG: A Knowledge Graph for Representing Cultural Heritage Objects and Digitisation Paradata[EB/OL]. (2025-05-20)[2025-07-04]. https://arxiv.org/abs/2505.13276.
[70] SANDERSON R.Implementing Linked Art in a Multi-Modal Database for Cross-Collection Discovery[J]. Open Library of Humanities, 2024, 10(2): 102.
[71] PENG Z L, WANG W H, DONG L, et al. Kosmos-2: Grounding Multimodal Large Language Models to the World[EB/OL]. (2023-06-26) [2025-05-15]. https://arxiv.org/abs/2306.14824.
[72] YASUNAGA M, REN H Y, BOSSELUT A, et al.QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering[C]// Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. OnlineAssociation for Computational Linguistics, 2021: 535-546.
[73] MAVROMATIS C, KARYPIS G. GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning [EB/OL]. (2024-05-30)[2026-03-04]. https://arxiv.org/abs/2405.20139
[74] AGRAWAL V, WANG F, PURI R. Query-Aware Graph Neural Networks for Enhanced Retrieval-Augmented Generation[EB/OL]. (2025-07-25)[2025-08-04]. https://arxiv.org/abs/2508.05647.
[75] SUN Y, SUN K, XU Y E, et al.KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering[C]// Findings of the Association for Computational Linguistics, Suzhou: EMNLP 2025. 2025: 6194-6216.
[76] SCARINGI R, FIAMENI G, VESSIO G, et al.GraphCLIP: Image-Graph Contrastive Learning for Multimodal Artwork Classification[J]. Knowledge-Based Systems, 2025, 310: 112857.
[77] LI Q Q, ZOU Q, MA D, et al.Dating Ancient Paintings of Mogao Grottoes Using Deeply Learnt Visual Codes[J]. Science China Information Sciences, 2018, 61(9): 092105.
[78] WANG X G, CHANG W L, TAN X.Representing and Linking Dunhuang Cultural Heritage Information Resources Using Knowledge Graph[J]. Knowledge Organization, 2020, 47(7): 604-615.
[79] VENKATESH K, DALVA Y, LOURENTZOU I, et al. Context Canvas: Enhancing Text-to-Image Diffusion Models with Knowledge Graph-Based RAG[EB/OL]. (2024-12-12)[2025-05-15]. https://arxiv.org/abs/2412.09614.
[80] YASUNAGA M, AGHAJANYAN A, SHI W J, et al. Retrieval-Augmented Multimodal Language Modeling [EB/OL]. (2022-11-22)[2025-05-15]. https://arxiv.org/abs/2211.12561.
[81] DUAN Z, ZHAO Q, CHEN C, et al. ArtAug: Enhancing Text-to-Image Generation through Synthesis-Understanding Interaction[EB/OL]. (2024-12-17) [2025-05-15]. https://arxiv.org/abs/2412.12888.
[82] AIVALIS T, KLAMPANOS I A, TROUMPOUKIS A, et al. Training Data Attribution for Image Generation using Ontology-Aligned Knowledge Graphs[J]. arXiv preprint arXiv:2512.02713, 2025.
[83] HUANG Y Y, YU S S, CHU J J, et al.Using Knowledge Graphs and Deep Learning Algorithms to Enhance Digital Cultural Heritage Management[J]. Heritage Science, 2023, 11: 204.
[84] HUANG S S, LI Q S, LIAO J, et al.Controllable Image Synthesis Methods, Applications and Challenges: A Comprehensive Survey[J]. Artificial Intelligence Review, 2024, 57(12): 336.
[85] ZHANG L M, RAO A Y, AGRAWALA M.Adding Conditional Control to Text-to-Image Diffusion Models[C]// 2023 IEEE/CVF International Conference on Computer Vision (ICCV). Paris: IEEE, 2024: 3813-3824.
[86] MOU C, WANG X T, XIE L B, et al.T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2024, 38(5): 4296-4304.
[87] ZHANG X Y.AI-Assisted Restoration of Yangshao Painted Pottery Using LoRA and Stable Diffusion[J]. Heritage, 2024, 7(11): 6282-6309.
[88] RUIZ N, LI Y Z, JAMPANI V, et al.DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation[C]// 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, BC: IEEE, 2023: 22500-22510.
[89] LIU J T, HUANG Y.LoRA-Fine-Tuned Latent Diffusion for High-Fidelity Digitization of Classic Mongolian Patterns[J]. Applied Sciences, 2025, 16(1): 11.
[90] GAL R, ALALUF Y, ATZMON Y, et al. An Image Is Worth One Word: Personalizing Text-to-Image Generation Using Textual Inversion[EB/OL]. (2022-08-02) [2025-05-15]. https://arxiv.org/abs/2208.01618.
[91] DU Y Q.Structural Knowledge-Guided Feature Inference Network for Image Inpainting[J]. International Journal of Circuits, Systems and Signal Processing, 2022, 16: 710-717.
[92] GUTIÉRREZ Y, SALAS J I A, MONTOYO A, et al. KD SENSO-MERGER: An Architecture for Semantic Integration of Heterogeneous Data[J]. Engineering Applications of Artificial Intelligence, 2024, 132: 107854.
[93] NOOR S, SHAH L, ADIL M, et al.Modeling and Representation of Built Cultural Heritage Data Using Semantic Web Technologies and Building Information Model[J]. Computational and Mathematical Organization Theory, 2019, 25(3): 247-270.
[94] XIA S P.Design Method Based on Extensible Semantic Representation Algorithm and Its Application in Product Packaging Design[J]. Service Oriented Computing and Applications, 2024:1-13.
[95] LI C L, YE Z W, WEN W, et al.Beyond Photorealism: An AIGC-Powered Framework for Stylized and Gamified Cultural Heritage Revitalization[J]. Buildings, 2025, 15(20): 3782.
[96] HAO Q B, ZHENG W G, WANG C D, et al.MLRN: A Multi-View Local Reconstruction Network for Single Image Restoration[J]. Information Processing & Management, 2024, 61(3): 103700.
[97] WANASKAR K, JENA G, EIRINAKI M.Multimodal Benchmarking and Recommendation of Text-to-Image Generation Models[C]// 2025 IEEE 11th International Conference on Big Data Computing Service and Machine Learning Applications (BigDataService). Piscataway: IEEE, 2025: 179-186.
[98] MARTINI M.A Simple Relationship between SSIM and PSNR for DCT-Based Compressed Images and Video: SSIM as Content-Aware PSNR[C]// 2023 IEEE 25th International Workshop on Multimedia Signal Processing (MMSP). Poitiers: IEEE, 2023: 1-5.
[99] YAURI-LOZANO E, CASTILLO-CARA M, OROZCO-BARBOSA L, et al.Generative Adversarial Networks for Text-to-Face Synthesis & Generation: A Quantitative-Qualitative Analysis of Natural Language Processing Encoders for Spanish[J]. Information Processing & Management, 2024, 61(3): 103667.
[100] LI X, WANG Z K, CHEN C, et al.SemID: Blind Image Inpainting with Semantic Inconsistency Detection[J]. Tsinghua Science and Technology, 2024, 29(4): 1053-1068.
[101] ZHANG Y, ZONG R H, KOU Z Y, et al.CollabLearn: An Uncertainty-Aware Crowd-AI Collaboration System for Cultural Heritage Damage Assessment[J]. IEEE Transactions on Computational Social Systems, 2022, 9(5): 1515-1529.
[102] MYERS D, DALGITY A, AVRAMIDES I, et al.Arches: An Open Source GIS for the Inventory and Management of Immovable Cultural Heritage[C]// Progress in Cultural Heritage Preservation. Berlin, Heidelberg: Springer, 2012: 817-824.
[103] PURDAY J.Think Culture: Europeana.eu from Concept to Construction[J]. The Electronic Library, 2009, 27(6): 919-937.
[104] HU X, HO E M Y, QIAO C. Digitizing Dunhuang Cultural Heritage: A User Evaluation of Mogao Cave Panorama Digital Library[J]. Journal of Data and Information Science, 2017, 2(3): 49-67.
[105] LUDLOW J B, MOL A.Digital imaging[J]. Oral Radiology: Principles and Interpretation. 7th ed. St Louis, Elsevier, 2014(7): 41-62.
[106] SHIVOTTAM J, MISHRA S.Tirtha - an Automated Platform to Crowdsource Images and Create 3D Models of Heritage Sites[C]// The 28th International ACM Conference on 3D Web Technology. San Sebastian: ACM, 2023: 1-15.
[107] MURPHY M, KRAJACIC P, MEEGAN E, et al.A Metadata/Paradata Design Framework for Historic BIM[M]// 3D Research Challenges in Cultural Heritage V. Cham: Springer Nature Switzerland, 2024: 127-138.
[108] BAEK S, HWANG H, PARK C W, et al. Development of an Artificial Intelligence-Based Platform for the Analysis and Utilization of Cultural Heritage Data[J]. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2025, X-M-2-2025: 39-46.
[109] XU Z S, YANG Y Q, FANG Q Z, et al.A Comprehensive Dataset for Digital Restoration of Dunhuang Murals[J]. Scientific Data, 2024, 11: 955.
[110] REN H, SUN K, ZHAO F H, et al.Dunhuang Murals Image Restoration Method Based on Generative Adversarial Network[J]. Heritage Science, 2024, 12: 39.
[111] MA W J, LUO X D, CHUBOTINA I, et al.Research on Iterative Design Strategies of Yao Traditional Patterns Based on AIGC[C]// Proceedings of the 2024 International Conference on Mathematics and Machine Learning. Nanjing: ACM, 2024: 194-201.
[112] WU H, ZHONG M Y, CHEN S, et al.Research on the Sanxingdui Cultural and Creative Product Design Based on an AIGC Design Framework[J]. Proceedings of the Design Society, 2025, 5: 2761-2769.
[113] WU F, HSIAO S W, LU P.An AIGC-Empowered Methodology to Product Color Matching Design[J]. Displays, 2024, 81: 102623.
[114] BANFI F, PONTISSO M, PAOLILLO F R, et al.Interactive and Immersive Digital Representation for Virtual Museum: VR and AR for Semantic Enrichment of Museo Nazionale Romano, Antiquarium Di Lucrezia Romana and Antiquarium Di Villa Dei Quintili[J]. ISPRS International Journal of Geo-Information, 2023, 12(2): 28.