Saved in:
Bibliographic Details
Main Authors: Li, Chang, Peng, Xingtao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.05949
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912695880515584
author Li, Chang
Peng, Xingtao
author_facet Li, Chang
Peng, Xingtao
contents Stereo image matching is a fundamental task in computer vision, photogrammetry and remote sensing, but there is an almost unexplored field, i.e., polygon matching, which faces the following challenges: disparity discontinuity, scale variation, training requirement, and generalization. To address the above-mentioned issues, this paper proposes a novel U(PM)$^2$: low-cost unsupervised polygon matching with pre-trained models by uniting automatically learned and handcrafted features, of which pipeline is as follows: firstly, the detector leverages the pre-trained segment anything model to obtain masks; then, the vectorizer converts the masks to polygons and graphic structure; secondly, the global matcher addresses challenges from global viewpoint changes and scale variation based on bidirectional-pyramid strategy with pre-trained LoFTR; finally, the local matcher further overcomes local disparity discontinuity and topology inconsistency of polygon matching by local-joint geometry and multi-feature matching strategy with Hungarian algorithm. We benchmark our U(PM)$^2$ on the ScanNet and SceneFlow datasets using our proposed new metric, which achieved state-of-the-art accuracy at a competitive speed and satisfactory generalization performance at low cost without any training requirement.
format Preprint
id arxiv_https___arxiv_org_abs_2511_05949
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle U(PM)$^2$:Unsupervised polygon matching with pre-trained models for challenging stereo images
Li, Chang
Peng, Xingtao
Computer Vision and Pattern Recognition
Stereo image matching is a fundamental task in computer vision, photogrammetry and remote sensing, but there is an almost unexplored field, i.e., polygon matching, which faces the following challenges: disparity discontinuity, scale variation, training requirement, and generalization. To address the above-mentioned issues, this paper proposes a novel U(PM)$^2$: low-cost unsupervised polygon matching with pre-trained models by uniting automatically learned and handcrafted features, of which pipeline is as follows: firstly, the detector leverages the pre-trained segment anything model to obtain masks; then, the vectorizer converts the masks to polygons and graphic structure; secondly, the global matcher addresses challenges from global viewpoint changes and scale variation based on bidirectional-pyramid strategy with pre-trained LoFTR; finally, the local matcher further overcomes local disparity discontinuity and topology inconsistency of polygon matching by local-joint geometry and multi-feature matching strategy with Hungarian algorithm. We benchmark our U(PM)$^2$ on the ScanNet and SceneFlow datasets using our proposed new metric, which achieved state-of-the-art accuracy at a competitive speed and satisfactory generalization performance at low cost without any training requirement.
title U(PM)$^2$:Unsupervised polygon matching with pre-trained models for challenging stereo images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.05949