This paper introduces a novel top-down representation approach for deformable image registration, which estimates the deformation field by capturing various short-and long-range flow features at different scale levels. As a Hierarchical Vision Transformer (H- ViT), we propose a dual self-attention and cross-attention mechanism that uses high-level features in the deformation field to represent low-level ones, enabling information streams in the deformation field across all voxel patch embeddings irrespective of their spatial proximity. Since high-level features contain abstract flow patterns, such patterns are expected to effectively contribute to the representation of the deformation field in lower scales. When the self-attention module utilizes within-scale short-range patterns for representation, the cross-attention modules dynamically look for the key tokens across different scales to further interact with the local query voxel patches. Our method shows superior accuracy and visual quality over the state-of-the-art registration methods in five publicly available datasets, highlighting a substantial enhancement in the performance of medical imaging registration. The project link is available at https://mogvision.github.io/hvit.

In this study, the authors address the fusion of low‐resolution multi‐spectral image with the corresponding high‐resolution panchromatic image to provide high‐resolution multi‐spectral (HRM) one, i.e. pan sharpening. The intensity–hue–saturation (IHS)‐based pan‐sharpening methods are popular because they are simple, efficient, and of high‐spatial quality. However, their frameworks are unavoidably subject to spectral distortion. To reduce the inevitable spectral distortion of IHS‐based pan‐sharpening approaches, the spectral consistency constraint is used in the proposed method. Moreover, to stabilise fusion results obtained from the ill‐posed pan‐sharpening problem and to keep the smoothness of the HRM image, a total variation regularisation term is considered. These considerations are formulated in a non‐quadratic optimisation problem. To solve this problem, a kind of variable splitting method, known as half‐quadratic approximation is utilised, and also an alternating optimisation procedure is used to reconstruct HRM image. To gain convenient control on the local spectral and the spatial information, and also to reduce the required memory, in the optimisation stage, the patch‐based strategy is employed. The proposed method was tested on two datasets acquired by GeoEye‐1 and Pleiades satellites. To evaluate the proposed method, visual assessment, as well as quantitative comparison with different pan‐sharpening methods, was carried out.