论文标题
D2D：用描述以检测方法的关键点提取
D2D: Keypoint Extraction with Describe to Detect Approach
论文作者
论文摘要
在本文中，我们提出了一种新颖的方法，该方法利用描述符空间中的信息提出关键点位置。然后检测到描述或共同检测和共同描述是提取本地描述符的两个典型策略。相反，我们提出了一种方法，该方法通过首先描述然后检测关键点位置来颠倒此过程。 ％描述对检测（D2D）利用成功的描述符模型，而无需进行任何额外的培训。我们的方法选择关键点作为具有高信息内容的显着位置，该位置由描述符定义，而不是某些独立运算符。我们对多个基准测试进行实验，包括图像匹配，摄像机定位和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，并且它跨方法和任务概括。
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.
