A Detector-Oblivious Multi-Arm Network for Keypoint Matching. Academic Article uri icon

abstract

  • This paper presents a matching network to establish point correspondence between images. We propose a Multi-Arm Network (MAN) capable of learning region overlap and depth, which can greatly improve keypoint matching robustness while bringing an extra 50% of computational time during the inference stage. By adopting a different design from the state-of-the-art learning based pipeline SuperGlue framework, which requires retraining when a different keypoint detector is adopted, our network can directly work with different keypoint detectors without time-consuming retraining processes. Comprehensive experiments conducted on four public benchmarks involving both outdoor and indoor scenarios demonstrate that our proposed MAN outperforms state-of-the-art methods.

published proceedings

  • IEEE Trans Image Process

author list (cited authors)

  • Shen, X., Hu, Q., Li, X., & Wang, C.

citation count

  • 1

complete list of authors

  • Shen, Xuelun||Hu, Qian||Li, Xin||Wang, Cheng

publication date

  • January 2023