SA-Homo: Scale Adaptive Homography Estimation for Scale Variation Scenarios

2026-06-29

AI Summary

This work addresses the significant performance degradation of conventional homography estimation methods when confronted with image pairs exhibiting large scale discrepancies. To tackle this challenge, the authors propose a scale-adaptive hierarchical alignment framework that achieves robust registration through a coarse-to-fine strategy. The core innovations include a scale-aware disparity bridging module, cascaded multi-scale linear attention, cross-scale similarity matrix blocks, and a lightweight iterative refinement module. Additionally, the study introduces HMSA, the first high-resolution, multi-modal satellite dataset specifically designed for evaluating large-scale variations. Experimental results demonstrate that the proposed method maintains high accuracy even under extreme scale differences up to 8×, substantially outperforming existing approaches and achieving state-of-the-art performance in both standard and extreme scale scenarios.

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

Problem

• Homography Estimation
• Scale Variation
• Scale Discrepancy
• Computer Vision
• Feature Consistency

Innovation

• Scale-adaptive homography estimation
• Multi-scale Linear Attention Cascade
• Cross-scale Similarity Matrix Block
• Iterative Homography Refinement
• HMSA dataset