Multi-Scale Dilated Attention-Based Transformer Network for Image Inpainting

The Pressure Sensitive Paint Technique (PSP) has gained attention in recent years because of its significant benefits in measuring surface pressure on wind tunnel models. However, in the post-processing process of PSP images, issues such as pressure taps, paint peeling, and contamination can lead to the loss of pressure data on the image, which seriously affects the subsequent calculation and analysis of pressure distribution. Therefore, image inpainting is particularly important in the post-processing process of PSP images. Deep learning offers new methods for PSP image inpainting, but some basic characteristics of convolutional neural networks (CNNs) may limit their ability to handle restoration tasks. By contrast, the self-attention mechanism in the transformer can efficiently model non-local relationships among input features by generating adaptive attention scores. As a result, we propose an efficient transformer network model for the PSP image inpainting task, named multi-scale dilated attention transformer (D-former). The model utilizes the redundancy of global dependencies modeling in Vision Transformers (ViTs) to introduce multi-scale dilated attention (MDA), this mechanism effectively models the interaction between localized and sparse patches within the shifted window, achieving a better balance between computational complexity and receptive field. As a result, D-former allows efficient modeling of long-range features while using fewer parameters and lower computational costs. The experiments on two public datasets and the PSP dataset indicate that the method in this article performs better compared to several advanced methods. Through the verification of real wind tunnel tests, this method can accurately restore the luminescent intensity data of holes in PSP images, thereby improving the accuracy of full field pressure data, and has a promising future in practical applications.