arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.13605cs.CVcs.LGeess.IV
收藏

D2D:基于描述检测方法的关键点提取

D2D: Keypoint Extraction with Describe to Detect Approach

Imperial College London(帝国理工学院);Scape Technologies(Scape科技公司)

Yurun Tian, Vassileios Balntas, Tony Ng, Axel Barroso-Laguna, Yiannis Demiris, Krystian Mikolajczyk

摘要:

在本文中,我们提出了一种新的方法,利用描述符空间内的信息,提出关键点的位置。先检测后描述或检测与描述联合是两种典型的局部描述符提取策略。相比之下,我们提出了一种方法,通过首先描述然后检测关键点位置来反转这个过程。% Describe-to-Detect(D2 D)利用成功的描述符模型,无需任何额外的训练。我们的方法选择关键点作为具有高信息含量的显著位置,其由描述符而不是一些独立的操作符定义。我们在多个基准上进行实验,包括图像匹配,相机定位和3D重建。结果表明,我们的方法提高了各种描述符的匹配性能,并且它在方法和任务中具有普遍性。

英文摘要:

In this paper, we present a novel approach that exploits the information within the descriptor space to propose keypoint locations. Detect then describe, or detect and describe jointly are two typical strategies for extracting local descriptors. In contrast, we propose an approach that inverts this process by first describing and then detecting the keypoint locations. % Describe-to-Detect (D2D) leverages successful descriptor models without the need for any additional training. Our method selects keypoints as salient locations with high information content which is defined by the descriptors rather than some independent operators. We perform experiments on multiple benchmarks including image matching, camera localisation, and 3D reconstruction. The results indicate that our method improves the matching performance of various descriptors and that it generalises across methods and tasks.

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。

↑