arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.08671cs.CVcs.AI
收藏

半稠密免检测器方法是否擅长匹配局部特征?

Are Semi-Dense Detector-Free Methods Good at Matching Local Features?

Univ. Bordeaux(波尔多大学);CNRS(法国国家科学研究中心);Bordeaux INP(波尔多国立综合理工学院);IMS(信息与信号处理研究所)

Matthieu Vilain, Rémi Giraud, Hugo Germain, Guillaume Bourmaud

AI总结:

本文研究SDF方法匹配能力与位姿估计质量的联系,提出SAM架构,发现在纹理区域限制匹配计算时,匹配精度与位姿估计准确性强相关。

摘要:

半稠密免检测器方法(SDF),如LoFTR,是目前最受欢迎的图像匹配方法之一。尽管SDF方法被训练用于在两幅图像之间建立对应关系,但其性能几乎完全使用相对位姿估计指标进行评估。因此,它们建立对应关系的能力与最终估计位姿质量之间的联系至今鲜少受到关注。本文是研究这一联系的首次尝试。我们首先提出了一种新颖的基于结构化注意力的图像匹配架构(SAM)。它使我们能够在两个数据集(MegaDepth和HPatches)上展示一个反直觉的结果:一方面,在位姿/单应性估计指标方面,SAM要么优于SDF方法,要么与之持平;但另一方面,在匹配精度方面,SDF方法显著优于SAM。随后,我们提议将匹配精度的计算限制在纹理区域,并表明在这种情况下SAM通常超越SDF方法。我们的发现强调了在纹理区域建立准确对应关系的能力与最终估计位姿/单应性的准确性之间存在强相关性。我们的代码将公开提供。

英文摘要:

Semi-dense detector-free approaches (SDF), such as LoFTR, are currently among the most popular image matching methods. While SDF methods are trained to establish correspondences between two images, their performances are almost exclusively evaluated using relative pose estimation metrics. Thus, the link between their ability to establish correspondences and the quality of the resulting estimated pose has thus far received little attention. This paper is a first attempt to study this link. We start with proposing a novel structured attention-based image matching architecture (SAM). It allows us to show a counter-intuitive result on two datasets (MegaDepth and HPatches): on the one hand SAM either outperforms or is on par with SDF methods in terms of pose/homography estimation metrics, but on the other hand SDF approaches are significantly better than SAM in terms of matching accuracy. We then propose to limit the computation of the matching accuracy to textured regions, and show that in this case SAM often surpasses SDF methods. Our findings highlight a strong correlation between the ability to establish accurate correspondences in textured regions and the accuracy of the resulting estimated pose/homography. Our code will be made available.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑