EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Beyond Single Descriptors: Complementary Feature Learning for Image Matching

Xianguo Yu, Yulong Feng, Xi Li

Journal of Imaging · 05.05.2026 · 12 (5) · 201

DOI: 10.3390/jimaging12050201 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 05.05.2026. Verfasst von Xianguo Yu und 2 weiteren Autor:innen. Beteiligte Einrichtung: College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Laboratory of Equipment State Sensing and Smart Support, Natural Science Foundation of Hunan Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sparse local feature matching has served as the cornerstone of numerous visual geometry tasks and attracted extensive attention. Although significant progress has been made in this area, improving the discriminative power of descriptors remains a key challenge. As far as we know, existing sparse feature matching methods only predict a single descriptor map for keypoints, which might restrict their potential in solving complex scenarios. This issue is particularly pronounced in real-time applications where most methods only learn descriptor maps at a reduced spatial resolution compared to the input image. Consequently, they require interpolating from the low resolution map for obtaining per-keypoint descriptors, which will introduce background contamination and reduce the discriminability of final descriptors. To address these issues, we propose an efficient novel complementary local feature description model. Specifically, the model simultaneously learns two descriptor maps using different loss functions within a single Convolutional Neural Network (CNN). An orthogonal loss is introduced to effectively coordinate the learning of the two branches, aiming to obtain decoupled and complementary descriptors. Extensive experiments across various visual geometry tasks, such as homography estimation, indoor and outdoor pose estimation, as well as visual localization, have demonstrated the superior performance of the proposed method.

Schlagwörter

Stichwörter der Autor:innen

complementary descriptorslocal feature matchingorthogonal losspose estimation

Autor:innen und Institutionen

  • College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China.
  • National Key Laboratory of Equipment State Sensing and Smart Support, National University of Defense Technology, Changsha 410073, China.
  • Hunan Provincial Key Laboratory of Flexible Electronic Materials Genome Engineering, Changsha University of Science and Technology, Changsha 410076, China.

Förderung

  • National Key Laboratory of Equipment State Sensing and Smart Support
  • Natural Science Foundation of Hunan Province

Zitieren

APA

Yu, X., Feng, Y., & Li, X. (2026). Beyond Single Descriptors: Complementary Feature Learning for Image Matching. Journal of Imaging, 12(5), 201. https://doi.org/10.3390/jimaging12050201

Vancouver

Yu X, Feng Y, Li X. Beyond Single Descriptors: Complementary Feature Learning for Image Matching. Journal of Imaging. 2026;12(5):201. doi:10.3390/jimaging12050201

BibTeX
@article{Yu2026,
  author = {Yu, Xianguo and Feng, Yulong and Li, Xi},
  title = {Beyond Single Descriptors: Complementary Feature Learning for Image Matching},
  journal = {Journal of Imaging},
  year = {2026},
  volume = {12},
  number = {5},
  pages = {201},
  doi = {10.3390/jimaging12050201}
}
Kostenlos starten →