Research on Restoration and Completion Algorithm of Cultural Relics Based on Generative Adversarial Network and Diffusion Model
Journal of Discovery Core · 19.11.2026 · 1 (3) · 1-28
DOI: 10.67541/jdc2613 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Discovery Core, online erschienen am 19.11.2026. Verfasst von Min Ma. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
A decision-level fusion framework was proposed to solve the problem that the texture generated by the generative adversarial network (GAN) is sharp, but the large-scale loss is easy to drift, and the complementarity of the diffusion model is coherent but the fine-grained texture is easy to over-smooth in the restoration of cultural relics. An asymmetric dual-stream generator with feature representation isolation is constructed, and a defect-aware routing controller is designed. The local edge density, fragment compactness, and neighborhood semantic gradient are taken as inputs, and the path is generated by pixelwise allocation through online preference mining. The routing weight modulates the cross-attention of the diffusion stream to the adversarial stream texture features by multiplicative gating, and reverse-infuses the low-level structure prior of the diffusion stream. An adaptive fusion operator guided by routing gradient is proposed to generate the bandwidth point by point according to the weighted gradient tensor and stretch it anisotropic along the main direction of the structure tensor. The three style anchoring constraints of stroke direction, pigment color moment and texture energy spectrum slope are introduced. On the hierarchical incomplete test set, the PSNR of the method reaches 28.94 dB and 25.31 dB in the transition interval from L2 to L3, which is 1.48 dB and 1.29 dB higher than the optimal shallow fusion baseline. The boundary LPIPS is reduced to 0.087, and the style distance is reduced to 0.108. Ablation experiments verify the independent contribution of routing mechanism and feature-level interaction and show that decision-level fusion can effectively realize the complementarity of the two streams under the capability constraints of the existing generation model.
Zitieren
APA
Ma, M. (2026). Research on Restoration and Completion Algorithm of Cultural Relics Based on Generative Adversarial Network and Diffusion Model. Journal of Discovery Core, 1(3), 1-28. https://doi.org/10.67541/jdc2613
Vancouver
Ma M. Research on Restoration and Completion Algorithm of Cultural Relics Based on Generative Adversarial Network and Diffusion Model. Journal of Discovery Core. 2026;1(3):1-28. doi:10.67541/jdc2613
BibTeX
@article{Ma2026,
author = {Ma, Min},
title = {Research on Restoration and Completion Algorithm of Cultural Relics Based on Generative Adversarial Network and Diffusion Model},
journal = {Journal of Discovery Core},
year = {2026},
volume = {1},
number = {3},
pages = {1--28},
doi = {10.67541/jdc2613}
}
EUVIMED