SA-Homo: Scale Adaptive Homography Estimation for Scale Variation Scenarios
2026-06-29 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address the problem of aligning images that differ greatly in scale, which is difficult for current deep learning methods. They propose SA-Homo, a new approach that first uses a global module to roughly align images with large scale differences and then refines the alignment locally with a lighter module. Their method uses special attention techniques to understand relationships between features even when scale varies. They also introduce a new satellite image dataset to test their approach and show it works better than existing methods, especially with big scale changes.
homography estimationscale variationdeep learningmulti-scale attentionfeature correlationimage alignmentsatellite imageryiterative refinementcross-scale similarityscale-adaptive frameworks
Authors
Shangxuan Xie, Haifeng Wu, Yuhang Wang, Huarong Jia, Wen Li
Abstract
Homography estimation, as one of the fundamental problems in computer vision, remains challenged by scale variation scenarios where image pairs potentially exhibit significant scale discrepancies. Existing deep learning frameworks frequently suffer from a significant performance degradation in such cases, as they rely on limited displacement assumptions and local feature consistency that might not hold under large scale gaps. In this paper, we propose SA-Homo, a novel scale-adaptive homography estimation framework designed to achieve robust alignment across a wide range of scale discrepancy ratios. We adopt a hierarchical scale alignment strategy that transitions from the global perspective with a heavy module to a local perspective with a light module. Specifically, we introduce the Scale-aware Discrepancy Bridging Module (SDBM) for initial alignment, which utilizes a Multi-scale Linear Attention Cascade (MLAC) to capture long-range dependencies and mitigate feature inconsistencies, along with a global Cross-scale Similarity Matrix Block (CSMB) for scale robust correlation representation. Once the initial scale gap is bridged, a lightweight Iterative Homography Estimation Refinement Module (IHERM) progressively polishes the result using local correlations. To facilitate this research, we contribute the HMSA dataset, a high-resolution, multi-modal satellite benchmark specifically tailored for scale-variant challenges. Extensive experiments demonstrate that SA-Homo maintains high precision even under 8$\times$ scale discrepancies, outperforming state-of-the-art methods in both conventional scale-similar scenarios and challenging scale variation scenarios. Code and collected datasets are available at https://github.com/shangxuanx330/SA_Homo