Generative deep learning provides new approaches for natural image restoration and structural reconstruction. However, virtually restoring Kizil cave murals remains difficult due to their unique artistic style, complex damage, and the need to preserve semantic consistency. This study proposes a multimodal controlled diffusion model that integrates textual and multi-dimensional visual features for high-precision restoration. The model leverages latent space diffusion for high-quality image generation and introduces structural constraints to improve semantic alignment and controllability. A dynamic feature-adaptive GSC (DFA-GSC) module captures local and global features through multi-scale convolution and an adaptive weight generator, enhancing texture perception. For damaged regions, a conditional matching loss helps refine both texture and structure. Experimental results demonstrate that compared to traditional CNNs and single diffusion models, the proposed method achieves superior performance in both evaluation metrics and visual quality.

The rejoining of bone sticks holds significant importance in studying the historical and cultural aspects of the Han Dynasty. Currently, the rejoining work of bone inscriptions heavily relies on manual efforts by experts, demanding a considerable amount of time and energy. This paper introduces a multi-scale feature fusion Siamese network guided by edge contour (MFS-GC) model. Constructing a Siamese network framework, it first uses a residual network to extract features of bone sticks, which is followed by computing the L2 distance for similarity measurement. During the extraction of feature vectors using the residual network, the BN layer tends to lose contour detail information, resulting in less conspicuous feature extraction, especially along fractured edges. To address this issue, the Spatially Adaptive DEnormalization (SPADE) model is employed to guide the normalization of contour images of bone sticks. This ensures that the network can learn multi-scale boundary contour features at each layer. Finally, the extracted multi-scale fused features undergo similarity measurement for local matching of bone stick fragment images. Additionally, a Conjugable Bone Stick Dataset (CBSD) is constructed. In the experimental validation phase, the MFS-GC algorithm is compared with classical similarity calculation methods in terms of precision, recall, and miss detection rate. The experiments demonstrate that the MFS-GC algorithm achieves an average accuracy of 95.5% in the Top-15 on the CBSD. The findings of this research can contribute to solving the rejoining issues of bone sticks.

Among the approximately 60,000 bone stick fragments unearthed from the Weiyang Palace site of the Han Dynasty, about 57,000 bear inscriptions. Most of these fragments exhibit vertical fractures, leading to a separation between the upper and lower fragments, which poses significant challenges to digital preservation and artifact restoration. Manual matching is inefficient and may cause further damage to the bone sticks. This paper proposes a novel multimodal bone stick matching approach that integrates image, inscription, and archeological information to enhance the accuracy and efficiency of matching fragmented bone stick artifacts. Unlike traditional methods that rely solely on image data, our method leverages large-scale pre-trained models, namely Vision-RWKV for visual feature extraction, RWKV for inscription analysis, and BERT for archeological metadata encoding. A dynamic cross-modal feature fusion mechanism is introduced to effectively combine these features, enabling better interaction and weighting based on the contextual relevance of each modality. This approach significantly improves matching performance, particularly in challenging cases involving fractures, corrosion, and missing sections. The novelty of this method lies in its ability to simultaneously extract and fuse multiple sources of information, addressing the limitations of traditional image-based matching methods. This paper uses Rank-N and Cumulative Match Characteristic (CMC) curves as evaluation metrics. Experimental evaluation shows that the matching accuracy reaches 94.73% at Rank-15, and the method performs significantly better than the comparative methods on the CMC evaluation curve, demonstrating outstanding performance. Overall, this approach significantly enhances the efficiency and accuracy of bone stick artifact matching, providing robust technical support for the research and restoration of bone stick cultural heritage.

The unearthed artifacts from the ruins of the Weiyang Palace in the Han Dynasty’s Chang’an City include a large number of bone stick relics. The front and back of each bone stick form a pair, with similar appearances within each pair, indicating a matching relationship. However, the close resemblance in shape and complex texture features of the bone sticks make traditional image matching methods inefficient and less accurate. To address these challenges, this paper proposes a ConvNeXt-based Siamese network for bone stick image matching, utilizing feature similarity metrics. The method introduces a polarized self-attention module to enhance the model’s focus on the edges and texture features of the bone sticks, thereby improving the feature extraction capability of the ConvNeXt network. The utilization of DIS-Net for background normalization reduces noise interference, enhancing the precision of model matching. The adaptive adjustment of the learning rate using the cosine annealing algorithm accelerates network convergence. Additionally, transfer learning and contrastive learning methods are employed to pre-train the network, expediting convergence and improving matching accuracy. Experimental results demonstrate that compared to Siamese network algorithms with backbone networks such as VGG16, ResNet50, and MobileNet, the proposed method achieves an accuracy of 88.46% and 80% at Rank-10. This indicates a higher matching accuracy, providing an effective solution for automated bone stick matching.

The properties of the same pigments in murals are affected by different concentrations and particle diameters, which cause the shape of the spectral reflectance data curve to vary, thus influencing the outcome of matching calculations. This paper proposes a spectral matching classification method of multi-state similar pigments based on feature differences. Fast principal component analysis (FPCA) was used to calculate the eigenvalue variance of pigment spectral reflectance, then applied to the original reflectance values for parameter characterization. We first projected the original spectral reflectance from the spectral space to the characteristic variance space to identify the spectral curve. Secondly, the relative distance between the eigenvalues in the eigen variance space is combined with the JS (Jensen-Shannon) divergence to express the difference between the two spectral distributions. The JS information divergence calculates the relative distance between the eigenvalues. Experimental results show that our classification method can be used to identify the spectral curves of the same pigment under different states. The value of the root means square error (RMSE) decreased by 12.0817, while the mean values of the mean absolute percentage error (MAPE) and R2 increased by 0.0965 and 0.2849, respectively. Compared with the traditional spectral matching algorithm, the recognition error was effectively reduced.