EUVIMEDEUVIMED entdecken
Crossref

MVP: One-Shot Object Pose Estimation by Matching With Visible Points

Wentao Cheng, Minxing Luo

IEEE Signal Processing Letters · 2024 · 31 · 2760-2764

DOI: 10.1109/lsp.2024.3472492 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2024. Verfasst von Wentao Cheng und 1 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 28 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We introduce a novel method for one-shot object pose estimation. Recent detector-free one-shot methods have achieved promising results for challenging low-textured objects. The features in a query image are directly matched with all features in an object point cloud reconstructed via Structure-from-Motion (SfM) techniques. Rejecting invisible 3D points, as well as associated features, is performed implicitly using a deep neural network that is trained specifically for feature matching. This tightly-coupled strategy is prone to preserve 3D points that are rarely visible from the query view. In contrast, we propose to prune such erroneous points using the explicit image-point relational graph, which is a lightweight by-product of the SfM reconstruction. By injecting the graph-based pruning into stacked feature transformers, our method is able to obtain high quality 2D-3D correspondences through matching with visible points in an early stage. The experiments demonstrate that our method outperforms state-of-the-art model-free one-shot methods with faster speed.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Cheng, W., & Luo, M. (2024). MVP: One-Shot Object Pose Estimation by Matching With Visible Points. IEEE Signal Processing Letters, 31, 2760-2764. https://doi.org/10.1109/lsp.2024.3472492

Vancouver

Cheng W, Luo M. MVP: One-Shot Object Pose Estimation by Matching With Visible Points. IEEE Signal Processing Letters. 2024;31:2760-2764. doi:10.1109/lsp.2024.3472492

BibTeX
@article{Cheng2024,
  author = {Cheng, Wentao and Luo, Minxing},
  title = {MVP: One-Shot Object Pose Estimation by Matching With Visible Points},
  journal = {IEEE Signal Processing Letters},
  year = {2024},
  volume = {31},
  pages = {2760--2764},
  doi = {10.1109/lsp.2024.3472492}
}
Kostenlos starten →