HomoFM: Deep Homography Estimation with Flow Matching

TL;DR

HomoFM introduces a novel flow matching approach for deep homography estimation, modeling a continuous velocity field for precise transformations and incorporating domain adaptation to improve robustness across different scenarios.

Contribution

The paper presents HomoFM, the first to apply flow matching to homography estimation, and integrates domain adaptation for enhanced robustness across diverse conditions.

Findings

Outperforms state-of-the-art methods in accuracy

Demonstrates robustness across different domains

Achieves high-precision transformations

Abstract

Deep homography estimation has broad applications in computer vision and robotics. Remarkable progresses have been achieved while the existing methods typically treat it as a direct regression or iterative refinement problem and often struggling to capture complex geometric transformations or generalize across different domains. In this work, we propose HomoFM, a new framework that introduces the flow matching technique from generative modeling into the homography estimation task for the first time. Unlike the existing methods, we formulate homography estimation problem as a velocity field learning problem. By modeling a continuous and point-wise velocity field that transforms noisy distributions into registered coordinates, the proposed network recovers high-precision transformations through a conditional flow trajectory. Furthermore, to address the challenge of domain shifts issue, e.g., the cases of multimodal matching or varying illumination scenarios, we integrate a gradient reversal layer (GRL) into the feature extraction backbone. This domain adaptation strategy explicitly constrains the encoder to learn domain-invariant representations, significantly enhancing the network's robustness. Extensive experiments demonstrate the effectiveness of the proposed method, showing that HomoFM outperforms state-of-the-art methods in both estimation accuracy and robustness on standard benchmarks. Code and data resource are available at https://github.com/hmf21/HomoFM.