The virtual restoration of historic murals holds immense importance in the realm of cultural heritage preservation. Currently, there are three primary technical issues. First and foremost, it is imperative to delineate the precise location where the mural necessitates restoration. Second, the original color of the mural has changed over time, resulting in a difference from its current appearance. Then, while the method utilizing convolutional neural networks is effective in restoring small defaced areas of murals, its effectiveness significantly diminishes when applied to larger areas. The primary objectives of this paper are as follows: (1) To determine the large and small areas to be restored, the authors employ hyperspectral super-pixel segmentation and support vector machine-Markov random field (SVM-MRF) classification. (2) The authors transform the hyperspectral mural images into more realistic and accurate red-green-blue (RGB) images using the Commission Internationale de l’Eclairage (CIE) standard colorimetric system. (3) The authors restored the images respectively using convolutional neural network and matching image block-based approaches depending on the size of the areas to be mended. The proposed method has enhanced the image quality assessment (IQA) in terms of both color quality and restoration effects. In contrast to the pseudo-color fusion method, the color optimization algorithm described in this research enhances the multi-scale image quality (MUSIQ) by 8.42%. The suggested technique enhances MUSIQ by 2.41% when compared to the convolutional neural network-based image inpainting algorithm.

Sanxingdui cultural relics are the precious cultural heritage of humanity with high values of history, science, culture, art and research. However, mainstream analytical methods are contacting and detrimental, which is unfavorable to the protection of cultural relics. This paper improves the accuracy of the extraction, location, and analysis of artifacts using hyperspectral methods. To improve the accuracy of cultural relic mining, positioning, and analysis, the segmentation algorithm of Sanxingdui cultural relics based on the spatial spectrum integrated network is proposed with the support of hyperspectral techniques. Firstly, region stitching algorithm based on the relative position of hyper spectrally collected data is proposed to improve stitching efficiency. Secondly, given the prominence of traditional HRNet (High-Resolution Net) models in high-resolution data processing, the spatial attention mechanism is put forward to obtain spatial dimension information. Thirdly, in view of the prominence of 3D networks in spectral information acquisition, the pyramid 3D residual network model is proposed to obtain internal spectral dimensional information. Fourthly, four kinds of fusion methods at the level of data and decision are presented to achieve cultural relic labeling. As shown by the experiment results, the proposed network adopts an integrated method of data-level and decision-level, which achieves the optimal average accuracy of identification 0.84, realizes shallow coverage of cultural relics labeling, and effectively supports the mining and protection of cultural relics.

The Terracotta Warriors of the Qin Shi Huang Mausoleum hold immense historical significance. However, during the excavation process, accurately locating and extracting the Terracotta Warriors presents substantial challenges. We conducted research to develop an extraction algorithm. (1) A hyperspectral model was established to extract features. (2) A visual and distance-based feature extraction model was established to simulate visual and distance information, enabling the extraction of multidimensional features. (3) A parallel deep network was constructed, integrating spectral information, simulated visual data, and distance information to accurately extract the Terracotta Warriors. To verify the effectiveness of the algorithm, we collected 51 sets of large-size hyperspectral data on site. Experimental results demonstrate that the algorithm achieves a Combination Measure of 93%, outperforming the traditional Graph-FCN algorithm with a score of 12%. The algorithm innovatively incorporates distance information to classify the Terracotta Warriors, achieving good results.

Multi-modal image segmentation is a key task in various fields such as urban planning, infrastructure monitoring, and environmental analysis. However, it remains challenging due to complex scenes, varying object scales, and the integration of heterogeneous data sources (such as RGB, depth maps, and infrared). To address these challenges, we proposed a novel multi-modal segmentation framework, DyFuseNet, which features dynamic adaptive windows and cross-scale feature fusion capabilities. This framework consists of three key components: (1) Dynamic Window Module (DWM), which uses dynamic partitioning and continuous position bias to adaptively adjust window sizes, thereby improving the representation of irregular and fine-grained objects; (2) Scale Context Attention (SCA), a hierarchical mechanism that associates local details with global semantics in a coarse-to-fine manner, enhancing segmentation accuracy in low-texture or occluded regions; and (3) Hierarchical Adaptive Fusion Architecture (HAFA), which aligns and fuses features from multiple modalities through shallow synchronization and deep channel attention, effectively balancing complementarity and redundancy. Evaluated on benchmark datasets (such as ISPRS Vaihingen and Potsdam), DyFuseNet achieved state-of-the-art performance, with mean Intersection over Union (mIoU) scores of 80.40% and 80.85%, surpassing MFTransNet by 1.91% and 1.77%, respectively. The model also demonstrated strong robustness in challenging scenes (such as building edges and shadowed objects), achieving an average F1 score of 85% while maintaining high efficiency (26.19 GFLOPs, 30.09 FPS), making it suitable for real-time deployment. This work presents a practical, versatile, and computationally efficient solution for multi-modal image analysis, with potential applications beyond remote sensing, including smart monitoring, industrial inspection, and multi-source data fusion tasks.