D2D: Keypoint Extraction with Describe to Detect Approach
This addresses a fundamental challenge in computer vision for tasks like image matching and 3D reconstruction, offering a novel inversion of standard methods.
The paper tackles the problem of keypoint extraction by inverting the typical process, proposing a describe-to-detect approach that uses descriptor information to propose keypoint locations, and results show improved matching performance across various descriptors and tasks.
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.