Cross-resolution image alignment is a key problem in multiscale gigapixel photography, which requires to estimate homography matrix using images with large resolution gap. Existing deep homography methods concatenate the input images or features, neglecting the explicit formulation of correspondences between them, which leads to degraded accuracy in cross-resolution challenges. In this paper, we consider the cross-resolution homography estimation as a multimodal problem, and propose a local transformer network embedded within a multiscale structure to explicitly learn correspondences between the multimodal inputs, namely, input images with different resolutions. The proposed local transformer adopts a local attention map specifically for each position in the feature. By combining the local transformer with the multiscale structure, the network is able to capture long-short range correspondences efficiently and accurately. Experiments on both the MS-COCO dataset and the real-captured cross-resolution dataset show that the proposed network outperforms existing state-of-the-art feature-based and deep-learning-based homography estimation methods, and is able to accurately align images under 10x resolution gap.

[arXiv] [Code(comming soon)]

Fig 2. Architecture of the proposed LocalTrans network for homography estimation. (a) Overall structure of the LocalTrans; (b) Architecture of the local transformer that captures correspondences in different scales via a local self-attention encoder module (SAEM) and a local transformer decoder module (TDM); (c) Architecture of the homography estimation module that adopts local attention maps and high-level feature as input to estimate homography matrices from coarse-to-fine.

Fig 3. The process of Local Attention Kernel (LAK).