English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The Yongle Palace murals, as valuable cultural heritage, have sufferedvarying degrees of damage, making their restoration of significant importance.However, the giant size and unique data of Yongle Palace murals presentchallenges for existing deep-learning based restoration methods: 1) Thedistinctive style introduces domain bias in traditional transfer learning-basedrestoration methods, while the scarcity of mural data further limits theapplicability of these methods. 2) Additionally, the giant size of these muralsresults in a wider range of defect types and sizes, necessitating models withgreater adaptability. Consequently, there is a lack of focus on deeplearning-based restoration methods for the unique giant murals of YonglePalace. Here, a 3M-Hybrid model is proposed to address these challenges.Firstly, based on the characteristic that the mural data frequency is prominentin the distribution of low and high frequency features, high and low frequencyfeatures are separately abstracted for complementary learning. Furthermore, weintegrate a pre-trained Vision Transformer model (VIT) into the CNN module,allowing us to leverage the benefits of a large model while mitigating domainbias. Secondly, we mitigate seam and structural distortion issues resultingfrom the restoration of large defects by employing a multi-scale andmulti-perspective strategy, including data segmentation and fusion.Experimental results demonstrate the efficacy of our proposed model. Inregular-sized mural restoration, it improves SSIM and PSNR by 14.61% and 4.73%,respectively, compared to the best model among four representative CNN models.Additionally, it achieves favorable results in the final restoration of giantmurals.

A 3M-Hybrid Model for the Restoration of Unique Giant Murals: A Case Study on the Murals of Yongle Palace