HomoFM: Deep Homography Estimation with Flow Matching

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: He, Mengfan, Sun, Liangzheng, Li, Chunyu, Meng, Ziyang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914280488566784
author He, Mengfan
Sun, Liangzheng
Li, Chunyu
Meng, Ziyang
author_facet He, Mengfan
Sun, Liangzheng
Li, Chunyu
Meng, Ziyang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_18222
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HomoFM: Deep Homography Estimation with Flow Matching
He, Mengfan
Sun, Liangzheng
Li, Chunyu
Meng, Ziyang
Computer Vision and Pattern Recognition
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.
title HomoFM: Deep Homography Estimation with Flow Matching
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.18222