LocalTrans: A Multiscale Local Transformer Network for Cross-Resolution Homography Estimation

TL;DR

This paper introduces LocalTrans, a multiscale local transformer network designed to improve cross-resolution homography estimation by explicitly modeling correspondences, achieving superior accuracy in aligning images with large resolution gaps.

Contribution

The paper proposes a novel local transformer embedded in a multiscale structure to explicitly learn correspondences between cross-resolution images, enhancing alignment accuracy.

Findings

Outperforms existing methods on MS-COCO and real datasets.

Accurately aligns images with up to 10x resolution difference.

Efficiently captures long-short range correspondences.

Abstract

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 $10\times$ resolution gap.