AI RESEARCH
From Pairs to Sequences: Track-Aware Policy Gradients for Keypoint Detection
arXiv CS.CV
•
ArXi:2602.20630v4 Announce Type: replace Keypoint-based matching is a fundamental component of modern 3D vision systems, such as Structure-from-Motion (SfM) and SLAM. Most existing learning-based methods are trained on image pairs, a paradigm that fails to explicitly optimize for the long-term trackability of keypoints across sequences under challenging viewpoint and illumination changes. In this paper, we reframe keypoint detection as a sequential decision-making problem. We