LAConv: Local Adaptive Convolution for Image Fusion
This addresses pixel-wise image fusion tasks like pansharpening and hyperspectral super-resolution, offering an incremental improvement with a novel convolution method.
The paper tackles the problem of uniform convolution kernels not fully perceiving pixel-level particularities in image fusion tasks by proposing a local adaptive convolution (LAConv) that dynamically adjusts to spatial locations, achieving state-of-the-art results in pansharpening and hyperspectral image super-resolution.
The convolution operation is a powerful tool for feature extraction and plays a prominent role in the field of computer vision. However, when targeting the pixel-wise tasks like image fusion, it would not fully perceive the particularity of each pixel in the image if the uniform convolution kernel is used on different patches. In this paper, we propose a local adaptive convolution (LAConv), which is dynamically adjusted to different spatial locations. LAConv enables the network to pay attention to every specific local area in the learning process. Besides, the dynamic bias (DYB) is introduced to provide more possibilities for the depiction of features and make the network more flexible. We further design a residual structure network equipped with the proposed LAConv and DYB modules, and apply it to two image fusion tasks. Experiments for pansharpening and hyperspectral image super-resolution (HISR) demonstrate the superiority of our method over other state-of-the-art methods. It is worth mentioning that LAConv can also be competent for other super-resolution tasks with less computation effort.