An Ancient Murals Inpainting Method Based on Bidirectional Feature Adaptation and Adversarial Generative Networks

To address the issue of varying degrees of damage in ancient Chinese murals due to their age and human-induced destruction, we propose a mural image restoration method based on bidirectional feature adaptation and adversarial generative networks. Firstly, we size and format the mural image. Subsequently, we construct an improved generator model that captures bidirectional semantic information, while introducing a spatial attention mechanism for adaptive feature enhancement for missing. Additionally, a spatial attention mechanism is introduced to adaptively enhance the features of known regions in the mural images. Furthermore, a discriminator model is constructed to discriminate between the restored mural images and real images, outputting a binary classification matrix. Finally, the network model is constrained by loss functions to generate mural images with rich textures. The experimental results show that the method realizes the restoration of mural images with different degrees of damage, and the restored mural images have finer texture information, which can contribute to the protection and inheritance of Chinese traditional culture.