Artificial Intelligence‐Assisted Fresco Restoration with Multiscale Line Drawing Generation

Abstract

In this article, we study the mural restoration work based on artificial intelligence-assisted multiscale trace generation. Firstly, we convert the fresco images to colour space to obtain the luminance and chromaticity component images; then we process each component image to enhance the edges of the exfoliated region using high and low hat operations; then we construct a multistructure morphological filter to smooth the noise of the image. Finally, the fused mask image is fused with the original mural to obtain the final calibration result. The fresco is converted to HSV colour space, and chromaticity, saturation, and luminance features are introduced; then the confidence term and data term are used to determine the priority of shedding boundary points; then a new block matching criterion is defined, and the best matching block is obtained to replace the block to be repaired based on the structural similarity between the block to be repaired and the matching block by global search; finally, the restoration result is converted to RGB colour space to obtain the final restoration result. An improved generative adversarial network structure is proposed to address the shortcomings of the existing network structure in mural defect restoration, and the effectiveness of the improved modules of the network is verified. Compared with the existing mural restoration algorithms on the test data experimentally verified, the peak signal-to-noise ratio (PSNR) score is improved by 4% and the structural similarity (SSIM) score is improved by 2%.

A multi-modal information fusion-based method for repairing cracks in train hooks

“…Generally captured train hook crack images often have large differences in fine grain size, due to the different scales of attribute regions in the image, if the image slicing method according to DAZLE if the slice size is fixed, when the attribute region is large, the information in a single slice is incomplete, easily leading to the loss of certain attribute features, and when the attribute region is small, the effective fine grain features captured within the image will be reduced [4]. In this chapter, to solve the problem of zero-sample fine-grained classification of train hook crack images, the DAZLE model is used as the baseline, and the attention mechanism based on multimodal information fusion attributes is used to fuse multi-scale image alignment methods to calculate the features of the most relevant image regions guided from the most relevant attributes to achieve effective recognition of train hook cracks, and the specific implementation steps are as follows [5].…”

Image restoration technology of Tang Dynasty tomb murals based on adversarial edge learning

“…PEI et al 9 used the Markov Random Field (MRF) model for repairing color enhancement and texture synthesis of ancient Chinese murals. Song et al 10 proposed a multi-scale intelligent restoration method for murals by improving the generative adversarial network structure. Zhou et al 11 proposed a deep learning-based and structure-guided approach for restoring Dunhuang mural images.…”

The Development Trend of Digital Art in the Age of Artificial Intelligence

“…Digital artistic creation has gradually become more intelligent, autonomous and diversified. Nowadays, AI has become an important tool for digital art creation, which can not only simulate the artist's creative process, but also produce unique and unprecedented works of art [2]. The digital art market has also achieved unprecedented development with the help of AI technology.…”