Find in Library

With the rise of downstream image tasks, the requirements for the quality of images obtained upstream are becoming higher and higher. In view of the many structural features of remote sensing images, we propose a novel deep neural network architecture for hyperspectral image fusion that integrates attention mechanisms and multi-layer perceptron blocks. The proposed network can capture long-range spatial dependencies between image elements, which is critical for capturing multi-scale features in remote sensing applications. The attention mechanisms selectively focus on important image features while disregarding redundant information, and the multi-layer perceptron blocks can capture multi-scale features by processing image features at different scales. The experimental results demonstrate that the proposed network outperforms other state-of-the-art methods in terms of both objective evaluation metrics and visual quality. The proposed method achieves higher Peak Signal to Noise Ratio and Spatial Consistency and Contrast values compared to other methods while preserving fine details and textures in the fused images. Overall, the proposed network provides an effective and efficient solution for hyperspectral image fusion that can contribute to the development of more accurate and reliable remote sensing applications.