arxiv: 2604.09367 · v1 · submitted 2026-04-10 · 💻 cs.CV

Recognition: unknown

EpiAgent: An Agent-Centric System for Ancient Inscription Restoration

Shipeng Zhu , Ang Chen , Na Nie , Pengfei Fang , Min-Ling Zhang , Hui Xue

Authors on Pith no claims yet

Pith reviewed 2026-05-10 16:57 UTC · model grok-4.3

classification 💻 cs.CV

keywords ancient inscriptionsinscription restorationagentic AILLM plannercultural heritagedigital restorationmultimodal AI

0 comments

The pith

An agent system using an LLM planner restores ancient inscriptions more effectively than rigid AI pipelines.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents EpiAgent, a system that treats the restoration of ancient inscriptions as a hierarchical planning task. An LLM acts as a central planner that follows an Observe-Conceive-Execute-Reevaluate cycle to combine visual and textual analysis with historical knowledge and specialized tools. This approach allows for adaptive, iterative refinement instead of fixed processing steps. The authors show that this leads to higher quality restorations and better handling of varied real-world damage on actual degraded inscriptions. If correct, it points to a way for AI to mimic expert human workflows in preserving cultural artifacts.

Core claim

EpiAgent formulates inscription restoration as a hierarchical planning problem. An LLM-based central planner orchestrates collaboration among multimodal analysis, historical experience, specialized restoration tools, and iterative self-refinement following the Observe-Conceive-Execute-Reevaluate paradigm. This agent-centric coordination produces a flexible and adaptive restoration process that achieves superior restoration quality and stronger generalization compared to existing rigid pipeline methods across real-world degraded inscriptions.

What carries the argument

The LLM-based central planner following the Observe-Conceive-Execute-Reevaluate paradigm to coordinate multimodal analysis, historical experience, restoration tools, and self-refinement.

If this is right

Enables flexible adaptation to complex and heterogeneous degradations in inscriptions.
Outperforms conventional single-pass methods in restoration quality.
Provides stronger generalization to real-world examples.
Advances toward expert-level agent-driven preservation of cultural heritage.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

Similar agent planning could apply to restoring other types of historical artifacts or documents.
The iterative reevaluation step may improve performance in other multimodal AI tasks involving uncertainty.
Testing on inscriptions from different historical periods could reveal the limits of the historical experience integration.

Load-bearing premise

An LLM-based central planner can reliably orchestrate multimodal analysis, historical experience, specialized restoration tools, and iterative self-refinement to produce better results than rigid pipelines on heterogeneous real-world degradations.

What would settle it

A controlled test on a diverse set of previously unseen degraded ancient inscriptions where EpiAgent fails to show measurable improvements in restoration quality metrics over baseline methods.

Figures

Figures reproduced from arXiv: 2604.09367 by Ang Chen, Hui Xue, Min-Ling Zhang, Na Nie, Pengfei Fang, Shipeng Zhu.

**Figure 2.** Figure 2: Illustration of the EpiAgent framework, which mimics [PITH_FULL_IMAGE:figures/full_fig_p002_2.png] view at source ↗

**Figure 3.** Figure 3: Illustration of the workflow of EpiAgent. The “MLLM”, “LRM”, “DAM”, “CLM”, and “CC” denote Multimodal Large Language [PITH_FULL_IMAGE:figures/full_fig_p003_3.png] view at source ↗

**Figure 4.** Figure 4: (a) Process of Specialized Restoration Tools; (b) Details of Multi-perspective Evaluation. [PITH_FULL_IMAGE:figures/full_fig_p004_4.png] view at source ↗

**Figure 5.** Figure 5: Restoration results of different methods on degraded inscription images. (a)-(b) are from Testing Set S, (c)-(d) belong to Testing [PITH_FULL_IMAGE:figures/full_fig_p006_5.png] view at source ↗

**Figure 6.** Figure 6: Exemplary comparison between different tool invocation sequences faced with (a) severely degraded (L3) and (b) slightly degraded [PITH_FULL_IMAGE:figures/full_fig_p007_6.png] view at source ↗

**Figure 8.** Figure 8: Quantitative comparison of restoration time and CLIP [PITH_FULL_IMAGE:figures/full_fig_p008_8.png] view at source ↗

read the original abstract

Ancient inscriptions, as repositories of cultural memory, have suffered from centuries of environmental and human-induced degradation. Restoring their intertwined visual and textual integrity poses one of the most demanding challenges in digital heritage preservation. However, existing AI-based approaches often rely on rigid pipelines, struggling to generalize across such complex and heterogeneous real-world degradations. Inspired by the skill-coordinated workflow of human epigraphers, we propose EpiAgent, an agent-centric system that formulates inscription restoration as a hierarchical planning problem. Following an Observe-Conceive-Execute-Reevaluate paradigm, an LLM-based central planner orchestrates collaboration among multimodal analysis, historical experience, specialized restoration tools, and iterative self-refinement. This agent-centric coordination enables a flexible and adaptive restoration process beyond conventional single-pass methods. Across real-world degraded inscriptions, EpiAgent achieves superior restoration quality and stronger generalization compared to existing methods. Our work marks an important step toward expert-level agent-driven restoration of cultural heritage. The code is available at https://github.com/blackprotoss/EpiAgent.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

EpiAgent puts forward a new agent-centric planning loop for inscription restoration and reports better results than rigid pipelines on real degraded examples.

read the letter

The main point is that this paper introduces EpiAgent, which treats restoration as hierarchical planning under an Observe-Conceive-Execute-Reevaluate cycle run by an LLM planner that pulls in multimodal analysis, historical knowledge, and specialized tools. That formulation is new relative to the fixed-pipeline work it cites, and the system description shows a coherent way to make the process adaptive to varied damage patterns instead of single-pass fixes. The experiments section includes direct comparisons on real-world inscriptions, with metrics that support claims of higher quality and better generalization, plus some analysis of the components. The GitHub release is a plus for anyone who wants to inspect the implementation. Overall the architecture holds together without obvious internal contradictions or unstated assumptions that would break the reported gains. The soft spot is the heavy dependence on the LLM planner staying reliable across different inscription styles and degradation types; if the planner hallucinates a bad sequence the whole loop can drift, and the paper does not appear to stress-test that edge case extensively. Dataset details and exact effect sizes are given but remain tied to the specific collection used, so the generalization edge is plausible but not yet proven across broader corpora. This is for people working on agent systems for narrow, high-stakes restoration tasks or digital heritage applications. It is grounded enough and novel enough to merit a serious referee rather than a desk reject.

Referee Report

0 major / 3 minor

Summary. The manuscript introduces EpiAgent, an agent-centric system for ancient inscription restoration. It formulates the task as a hierarchical planning problem solved via an LLM-based central planner that coordinates multimodal analysis, historical experience, specialized restoration tools, and iterative self-refinement following an Observe-Conceive-Execute-Reevaluate loop. The authors claim this yields superior restoration quality and stronger generalization than existing rigid-pipeline methods across real-world degraded inscriptions, with code released at https://github.com/blackprotoss/EpiAgent.

Significance. If the reported empirical gains hold under rigorous evaluation, the work is significant for digital heritage preservation: it shows how agentic orchestration can adapt to heterogeneous degradations where fixed pipelines fail. The public code release is a clear strength that supports reproducibility and extension by the community.

minor comments (3)

[Abstract] Abstract: the superiority claim is stated without any numerical metrics, baselines, dataset sizes, or error bars, forcing readers to reach the experiments section to assess the central empirical result.
[Method] The description of how the LLM planner selects and sequences tools (multimodal analysis, historical lookup, restoration operators) would benefit from an explicit decision diagram or pseudocode listing the action space and termination criteria.
[Experiments] Experiments: while the abstract asserts stronger generalization, the manuscript should explicitly state the train/test split protocol, the number of real-world inscriptions used, and whether any held-out degradation types were evaluated.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the positive summary of EpiAgent, the recognition of its significance for digital heritage preservation, and the recommendation of minor revision. The referee's description correctly identifies the hierarchical planning formulation, the LLM-based central planner, the Observe-Conceive-Execute-Reevaluate loop, and the advantages over rigid pipelines, as well as the value of the public code release.

Circularity Check

0 steps flagged

No significant circularity

full rationale

The paper describes an LLM-orchestrated agent system (Observe-Conceive-Execute-Reevaluate) for inscription restoration and reports empirical gains over baselines on real-world data. No equations, fitted parameters, derivations, or self-referential definitions appear in the provided text or abstract. The central claim is an empirical performance comparison rather than a mathematical reduction; the architecture is presented as a design choice inspired by human workflows, with no load-bearing step that collapses to its own inputs by construction or via self-citation chains. This is a standard non-circular empirical systems paper.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The abstract describes a proposed software system without explicit mathematical models, fitted parameters, axioms, or new postulated entities; no ledger items are identifiable from the provided text.

pith-pipeline@v0.9.0 · 5489 in / 1150 out tokens · 52124 ms · 2026-05-10T16:57:13.086809+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

48 extracted references · 7 canonical work pages · 4 internal anchors

[1]

Restoring ancient text using deep learning: a case study on greek epigraphy

Yannis Assael, Thea Sommerschield, and Jonathan Prag. Restoring ancient text using deep learning: a case study on greek epigraphy. InProceedings of the Conference on Empir- ical Methods in Natural Language Processing, pages 6368– 6375, 2019. 3

2019
[2]

Restoring and attributing ancient texts using deep neural net- works.Nature, 603(7900):280–283, 2022

Yannis Assael, Thea Sommerschield, Brendan Shillingford, Mahyar Bordbar, John Pavlopoulos, Marita Chatzipanagiotou, Ion Androutsopoulos, Jonathan Prag, and Nando de Freitas. Restoring and attributing ancient texts using deep neural net- works.Nature, 603(7900):280–283, 2022. 3

2022
[3]

Character segmentation and restoration of qin-han bamboo slips using local auto-focus thresholding method

Songxiao Cao, Zichao Shu, Zhipeng Xu, Dailiang Xie, and Ya Xu. Character segmentation and restoration of qin-han bamboo slips using local auto-focus thresholding method. Multimedia Tools and Applications, 81(6):8199–8213, 2022. 3

2022
[4]

Restoreagent: Autonomous image restoration agent via multimodal large language models

Haoyu Chen, Wenbo Li, Jinjin Gu, Jingjing Ren, Sixiang Chen, Tian Ye, Renjing Pei, Kaiwen Zhou, Fenglong Song, and Lei Zhu. Restoreagent: Autonomous image restoration agent via multimodal large language models. InAdvances in Neural Information Processing Systems, pages 110643– 110666, 2024. 2, 3, 6

2024
[5]

Oracle bone inscription image restoration via glyph extraction.npj Heritage Science, 13(1): 321, 2025

Xiaolei Diao, Daqian Shi, Wei Cao, Ting Wang, Ruihua Qi, Chuntao Li, and Hao Xu. Oracle bone inscription image restoration via glyph extraction.npj Heritage Science, 13(1): 321, 2025. 3

2025
[6]

Phydae: Physics-guided degradation-adaptive experts for all-in-one remote sensing image restoration.IEEE Transactions on Geoscience and Remote Sensing, 64:1–18, 2026

Zhe Dong, Zhengning Zhang, Yuzhe Sun, Haochen Jiang, Tianzhu Liu, and Yanfeng Gu. Phydae: Physics-guided degradation-adaptive experts for all-in-one remote sensing image restoration.IEEE Transactions on Geoscience and Remote Sensing, 64:1–18, 2026. 3

2026
[7]

Restoring ancient ideo- graph: A multimodal multitask neural network approach

Siyu Duan, Jun Wang, and Qi Su. Restoring ancient ideo- graph: A multimodal multitask neural network approach. In Proceedings of the Joint International Conference on Com- putational Linguistics, Language Resources and Evaluation, pages 14005–14015, 2024. 2, 3

2024
[8]

Dong Guo, Faming Wu, Feida Zhu, Fuxing Leng, Guang Shi, Haobin Chen, Haoqi Fan, Jian Wang, Jianyu Jiang, Jiawei Wang, et al. Seed1. 5-vl technical report.arXiv preprint arXiv:2505.07062, 2025. 4

work page internal anchor Pith review arXiv 2025
[9]

Mambair: A simple baseline for image restoration with state-space model

Hang Guo, Jinmin Li, Tao Dai, Zhihao Ouyang, Xudong Ren, and Shu-Tao Xia. Mambair: A simple baseline for image restoration with state-space model. InProceedings of the European Conference on Computer Vision, pages 222–241,
[10]

Denoising diffu- sion probabilistic models.Advances in neural information processing systems, 33:6840–6851, 2020

Jonathan Ho, Ajay Jain, and Pieter Abbeel. Denoising diffu- sion probabilistic models.Advances in neural information processing systems, 33:6840–6851, 2020. 4

2020
[11]

Lora: Low-rank adaptation of large language models.Proceedings of the International Conference of Learning Representation,

Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. Lora: Low-rank adaptation of large language models.Proceedings of the International Conference of Learning Representation,
[12]

A survey on all-in-one image restoration: Tax- onomy, evaluation and future trends.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025

Junjun Jiang, Zengyuan Zuo, Gang Wu, Kui Jiang, and Xi- anming Liu. A survey on all-in-one image restoration: Tax- onomy, evaluation and future trends.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025. 2, 3

2025
[13]

Multi-agent image restoration.arXiv preprint arXiv:2503.09403, 2025

Xu Jiang, Gehui Li, Bin Chen, and Jian Zhang. Multi-agent image restoration.arXiv preprint arXiv:2503.09403, 2025. 3

work page arXiv 2025
[14]

Musiq: Multi-scale image quality transformer

Junjie Ke, Qifei Wang, Yilin Wang, Peyman Milanfar, and Feng Yang. Musiq: Multi-scale image quality transformer. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 5148–5157, 2021. 6

2021
[15]

Hybrid agents for image restoration.arXiv preprint arXiv:2503.10120, 2025

Bingchen Li, Xin Li, Yiting Lu, and Zhibo Chen. Hy- brid agents for image restoration.arXiv preprint arXiv:2503.10120, 2025. 3

work page arXiv 2025
[16]

A structural information-guided cross-modal method for dam- aged inscription inpainting via vision-language models.npj Heritage Science, 13(1):485, 2025

Yunjing Liu, Erhu Zhang, Guangfeng Lin, and Jinghong Duan. A structural information-guided cross-modal method for dam- aged inscription inpainting via vision-language models.npj Heritage Science, 13(1):485, 2025. 3

2025
[17]

Archaeology and epigraphy in the digital era.Journal of Archaeological Research, 30(2):285– 320, 2022

Mallory E Matsumoto. Archaeology and epigraphy in the digital era.Journal of Archaeological Research, 30(2):285– 320, 2022. 1, 3

2022
[18]

Method- ology and application of the kruskal-wallis test.Applied Mechanics and Materials, 611:115–120, 2014

Eva Ostertagova, Oskar Ostertag, and Jozef Kov´aˇc. Method- ology and application of the kruskal-wallis test.Applied Mechanics and Materials, 611:115–120, 2014. 6

2014
[19]

A generative model for the mycenaean linear b script and its application in infilling text from ancient tablets

Katerina Papavassileiou, Dimitrios I Kosmopoulos, and Gareth Owens. A generative model for the mycenaean linear b script and its application in infilling text from ancient tablets. ACM Journal on Computing and Cultural Heritage, 16(3): 1–25, 2023. 3

2023
[20]

Promptir: Prompting for all-in-one im- age restoration.Advances in Neural Information Processing Systems, 36:71275–71293, 2023

Vaishnav Potlapalli, Syed Waqas Zamir, Salman H Khan, and Fahad Shahbaz Khan. Promptir: Prompting for all-in-one im- age restoration.Advances in Neural Information Processing Systems, 36:71275–71293, 2023. 3, 5, 6

2023
[21]

Publications Office of the European Union, 2025

Erasmo Purificato, Danai Bili, Robert Jungnickel, Serra Victo- ria Ruiz, Josefina Faniani, Dias Abendroth, Llorca David Fer- nandez, and Emilia Gomez.The role of artificial intelligence in scientific research. Publications Office of the European Union, 2025. 1

2025
[22]

Charformer: A glyph fusion based attentive framework for high-precision character image de- noising

Daqian Shi, Xiaolei Diao, Lida Shi, Hao Tang, Yang Chi, Chuntao Li, and Hao Xu. Charformer: A glyph fusion based attentive framework for high-precision character image de- noising. InProceedings of the ACM International Conference on Multimedia, pages 1147–1155, 2022. 2, 3, 5, 6, 7

2022
[23]

Visual text processing: A com- prehensive review and unified evaluation.arXiv preprint arXiv:2504.21682, 2025

Yan Shu, Weichao Zeng, Fangmin Zhao, Zeyu Chen, Zhen- hang Li, Xiaomeng Yang, Yu Zhou, Paolo Rota, Xiang Bai, Lianwen Jin, et al. Visual text processing: A com- prehensive review and unified evaluation.arXiv preprint arXiv:2504.21682, 2025. 3

work page arXiv 2025
[24]

Machine learning for ancient languages: A survey.Computa- tional Linguistics, 49(3):703–747, 2023

Thea Sommerschield, Yannis Assael, John Pavlopoulos, Vanessa Stefanak, Andrew Senior, Chris Dyer, John Bodel, Jonathan Prag, Ion Androutsopoulos, and Nando De Freitas. Machine learning for ancient languages: A survey.Computa- tional Linguistics, 49(3):703–747, 2023. 2

2023
[25]

Black tigers: A grammar of chinese rubbings

Kenneth Starr. Black tigers: A grammar of chinese rubbings. InBlack Tigers. University of Washington Press, 2018. 1

2018
[26]

Tsinit: A two-stage inpainting network for incomplete text.IEEE Transactions on Multimedia, 25:5166– 5177, 2022

Jiande Sun, Fanfu Xue, Jing Li, Lei Zhu, Huaxiang Zhang, and Jia Zhang. Tsinit: A two-stage inpainting network for incomplete text.IEEE Transactions on Multimedia, 25:5166– 5177, 2022. 3

2022
[27]

Nima: Neural image assessment.IEEE Transactions on Image Processing, 27(8): 3998–4011, 2018

Hossein Talebi and Peyman Milanfar. Nima: Neural image assessment.IEEE Transactions on Image Processing, 27(8): 3998–4011, 2018. 6 9

2018
[28]

Kimi K2: Open Agentic Intelligence

Kimi Team, Yifan Bai, Yiping Bao, Guanduo Chen, Jiahao Chen, Ningxin Chen, Ruijue Chen, Yanru Chen, Yuankun Chen, Yutian Chen, et al. Kimi k2: Open agentic intelligence. arXiv preprint arXiv:2507.20534, 2025. 4

work page internal anchor Pith review arXiv 2025
[29]

Qwen2 Technical Report

Qwen Team et al. Qwen2 technical report.arXiv preprint arXiv:2407.10671, 2024. 4

work page internal anchor Pith review Pith/arXiv arXiv 2024
[30]

Chinese character inpainting with contextual semantic constraints

Jiahao Wang, Gang Pan, Di Sun, and Jiawan Zhang. Chinese character inpainting with contextual semantic constraints. In Proceedings of the ACM International Conference on Multi- media, pages 1829–1837, 2021. 3

2021
[31]

Ex- ploring clip for assessing the look and feel of images

Jianyi Wang, Kelvin CK Chan, and Chen Change Loy. Ex- ploring clip for assessing the look and feel of images. In Proceedings of the Annual AAAI Conference on Artificial Intelligence, pages 2555–2563, 2023. 6

2023
[32]

Image quality assessment: From error visibility to structural similarity.IEEE Transactions on Image Processing, 13(4):600–612, 2004

Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. Image quality assessment: From error visibility to structural similarity.IEEE Transactions on Image Processing, 13(4):600–612, 2004. 6

2004
[33]

Glyphsr: A simple glyph-aware framework for scene text image super-resolution

Baole Wei, Yuxuan Zhou, Liangcai Gao, and Zhi Tang. Glyphsr: A simple glyph-aware framework for scene text image super-resolution. InProceedings of the Annual AAAI Conference on Artificial Intelligence, pages 8277–8285, 2025. 3

2025
[34]

C-Pack: Packed Resources For General Chinese Embeddings

Shitao Xiao, Zheng Liu, Peitian Zhang, and Niklas Muen- nighoff. C-pack: Packaged resources to advance general chinese embedding.arXiv preprint arXiv:2309.07597, 2023. 4

work page internal anchor Pith review arXiv 2023
[35]

Maniqa: Multi-dimension attention network for no-reference image quality assessment

Sidi Yang, Tianhe Wu, Shuwei Shi, Shanshan Lao, Yuan Gong, Mingdeng Cao, Jiahao Wang, and Yujiu Yang. Maniqa: Multi-dimension attention network for no-reference image quality assessment. InProceedings of the IEEE/CVF Con- ference on Computer Vision and Pattern Recognition, pages 1191–1200, 2022. 6

2022
[36]

Docdiff: Document enhancement via residual dif- fusion models

Zongyuan Yang, Baolin Liu, Yongping Xxiong, Lan Yi, Guibin Wu, Xiaojun Tang, Ziqi Liu, Junjie Zhou, and Xing Zhang. Docdiff: Document enhancement via residual dif- fusion models. InProceedings of the ACM International Conference on Multimedia, pages 2795–2806, 2023. 3, 5, 6

2023
[37]

Predicting the original ap- pearance of damaged historical documents

Zhenhua Yang, Dezhi Peng, Yongxin Shi, Yuyi Zhang, Chongyu Liu, and Lianwen Jin. Predicting the original ap- pearance of damaged historical documents. InProceedings of the Annual AAAI Conference on Artificial Intelligence, pages 9382–9390, 2025. 3, 6

2025
[38]

Com- plexity experts are task-discriminative learners for any image restoration

Eduard Zamfir, Zongwei Wu, Nancy Mehta, Yuedong Tan, Danda Pani Paudel, Yulun Zhang, and Radu Timofte. Com- plexity experts are task-discriminative learners for any image restoration. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12753– 12763, 2025. 3, 5, 6

2025
[39]

Restormer: Efficient transformer for high-resolution image restoration

Syed Waqas Zamir, Aditya Arora, Salman Khan, Mu- nawar Hayat, Fahad Shahbaz Khan, and Ming-Hsuan Yang. Restormer: Efficient transformer for high-resolution image restoration. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5728–5739,
[40]

Docres: A generalist model toward uni- fying document image restoration tasks

Jiaxin Zhang, Dezhi Peng, Chongyu Liu, Peirong Zhang, and Lianwen Jin. Docres: A generalist model toward uni- fying document image restoration tasks. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 15654–15664, 2024. 3

2024
[41]

The unreasonable effectiveness of deep fea- tures as a perceptual metric

Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang. The unreasonable effectiveness of deep fea- tures as a perceptual metric. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 586–595, 2018. 6

2018
[42]

Icdar 2019 robust reading challenge on reading chinese text on signboard

Rui Zhang, Yongsheng Zhou, Qianyi Jiang, Qi Song, Nan Li, Kai Zhou, Lei Wang, Dong Wang, Minghui Liao, Mingkun Yang, et al. Icdar 2019 robust reading challenge on reading chinese text on signboard. InProceedings of the International Conference on Dcument Analysis and Recognition, pages 1577–1581. IEEE, 2019. 6

2019
[43]

Deep long-tailed learning: A survey.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(9):10795–10816, 2023

Yifan Zhang, Bingyi Kang, Bryan Hooi, Shuicheng Yan, and Jiashi Feng. Deep long-tailed learning: A survey.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(9):10795–10816, 2023. 6

2023
[44]

Reviving cultural heritage: A novel approach for compre- hensive historical document restoration

Yuyi Zhang, Peirong Zhang, Zhenhua Yang, Pengyu Yan, Yongxin Shi, Pengwei Liu, Fengjun Guo, and Lianwen Jin. Reviving cultural heritage: A novel approach for compre- hensive historical document restoration. InProceedings of the Annual Meeting of the Association for Computational Linguistics, pages 28876–28892, 2025. 2, 3, 6

2025
[45]

Ea-gan: Restoration of text in ancient chi- nese books based on an example attention generative adver- sarial network.Heritage Science, 2023

Wenjun Zheng, Benpeng Su, Ruiqi Feng, Xihua Peng, and Shanxiong Chen. Ea-gan: Restoration of text in ancient chi- nese books based on an example attention generative adver- sarial network.Heritage Science, 2023. 2, 3

2023
[46]

An intelligent agentic system for complex image restoration problems

Kaiwen Zhu, Jinjin Gu, Zhiyuan You, Yu Qiao, and Chao Dong. An intelligent agentic system for complex image restoration problems. InProceedings of the International Conference on Learning Representations, 2025. 2, 3, 6

2025
[47]

Text image inpainting via global structure-guided diffusion models

Shipeng Zhu, Pengfei Fang, Chenjie Zhu, Zuoyan Zhao, Qiang Xu, and Hui Xue. Text image inpainting via global structure-guided diffusion models. InProceedings of the Annual AAAI Conference on Artificial Intelligence, pages 7775–7783, 2024. 3, 5, 6

2024
[48]

Reproducing the past: A dataset for bench- marking inscription restoration

Shipeng Zhu, Hui Xue, Na Nie, Chenjie Zhu, Haiyue Liu, and Pengfei Fang. Reproducing the past: A dataset for bench- marking inscription restoration. InProceedings of the ACM International Conference on Multimedia, pages 7714—-7723,