ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ni, Junjie, Zhang, Guofeng, Li, Guanglin, Li, Yijin, Liu, Xinyang, Huang, Zhaoyang, Bao, Hujun
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915098278232064
author Ni, Junjie
Zhang, Guofeng
Li, Guanglin
Li, Yijin
Liu, Xinyang
Huang, Zhaoyang
Bao, Hujun
author_facet Ni, Junjie
Zhang, Guofeng
Li, Guanglin
Li, Yijin
Liu, Xinyang
Huang, Zhaoyang
Bao, Hujun
contents We tackle the efficiency problem of learning local feature matching. Recent advancements have given rise to purely CNN-based and transformer-based approaches, each augmented with deep learning techniques. While CNN-based methods often excel in matching speed, transformer-based methods tend to provide more accurate matches. We propose an efficient transformer-based network architecture for local feature matching. This technique is built on constructing multiple homography hypotheses to approximate the continuous correspondence in the real world and uni-directional cross-attention to accelerate the refinement. On the YFCC100M dataset, our matching accuracy is competitive with LoFTR, a state-of-the-art transformer-based architecture, while the inference speed is boosted to 4 times, even outperforming the CNN-based methods. Comprehensive evaluations on other open datasets such as Megadepth, ScanNet, and HPatches demonstrate our method's efficacy, highlighting its potential to significantly enhance a wide array of downstream applications.
format Preprint
id arxiv_https___arxiv_org_abs_2410_22733
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses
Ni, Junjie
Zhang, Guofeng
Li, Guanglin
Li, Yijin
Liu, Xinyang
Huang, Zhaoyang
Bao, Hujun
Computer Vision and Pattern Recognition
We tackle the efficiency problem of learning local feature matching. Recent advancements have given rise to purely CNN-based and transformer-based approaches, each augmented with deep learning techniques. While CNN-based methods often excel in matching speed, transformer-based methods tend to provide more accurate matches. We propose an efficient transformer-based network architecture for local feature matching. This technique is built on constructing multiple homography hypotheses to approximate the continuous correspondence in the real world and uni-directional cross-attention to accelerate the refinement. On the YFCC100M dataset, our matching accuracy is competitive with LoFTR, a state-of-the-art transformer-based architecture, while the inference speed is boosted to 4 times, even outperforming the CNN-based methods. Comprehensive evaluations on other open datasets such as Megadepth, ScanNet, and HPatches demonstrate our method's efficacy, highlighting its potential to significantly enhance a wide array of downstream applications.
title ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.22733