Digital rock resolution enhancement and detail recovery with multi attention neural network

Abstract

High-quality digital rock images are essential for subsequent high-precision numerical simulations. But limited by the imaging capability of computed tomography (CT), high resolution digital rock images with wide imaging field of view (FOV) cannot be acquired simultaneously. To cope with this constraint, we propose a novel Multi Attention Super-Resolution Neural Network (MASR) that enhances the resolution of images with wide FOV. Considering that textures and edges are more crucial in digital rocks, MASR introduces the component attention mechanism of Component Divide-and-Conquer Super-Resolution (CDCSR) model. By redesigning the hourglass network with spatial and channel attention mechanisms, proposing a spatial attention-based mask module, and optimizing the component attention mask calculation process, MASR delivers higher information utilization with fewer parameters and faster training than CDCSR. In addition, we optimize the depth of MASR to trade off speed and super-resolution quality. Furthermore, we retrain several state-of-the-art models. Through quantitative evaluations and qualitative visualizations, it is verified that MASR can recover sharper edges while removing noise, and obtain digital rock images with superior quality and reliability. The pixel-wise relative errors of MASR reconstructions are reduced by 15%–26% over bicubic interpolation method. Our codes and pretrained model are publicly available at https://github.com/MHDXing/MASR-for-Digital-Rock-Images.