EUVIMEDEUVIMED entdecken
Crossref

High-Resolution Open-Vocabulary Object 6D Pose Estimation

Jaime Corsetti, Davide Boscaini, Francesco Giuliari, Changjae Oh, Andrea Cavallaro, Fabio Poiesi

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-02 · 48 (2) · 2066-2077

DOI: 10.1109/tpami.2025.3624589 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-02. Verfasst von Jaime Corsetti und 5 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 62 Literaturangaben. Gefördert von: European Union’s Horizon Europe Research and Innovation Programme, AI-PRISM, Tier 2 HPC facility JADE2.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The generalisation to unseen objects in the 6D pose estimation task is very challenging. While Vision-Language Models (VLMs) enable using natural language descriptions to support 6D pose estimation of unseen objects, these solutions underperform compared to model-based methods. In this work we present Horyon, an open-vocabulary VLM-based architecture that addresses relative pose estimation between two scenes of an unseen object, described by a textual prompt only. We use the textual prompt to identify the unseen object in the scenes and then obtain high-resolution multi-scale features. These features are used to extract cross-scene matches for registration. We evaluate our model on a benchmark with a large variety of unseen objects across four datasets, namely REAL275, Toyota-Light, Linemod, and YCB-Video. Our method achieves state-of-the-art performance on all datasets, outperforming by 12.6 in Average Recall the previous best-performing approach.

Förderung

  • European Union’s Horizon Europe Research and Innovation Programme
  • AI-PRISM
  • Tier 2 HPC facility JADE2

Zitieren

APA

Corsetti, J., Boscaini, D., Giuliari, F., Oh, C., Cavallaro, A., & Poiesi, F. (2026). High-Resolution Open-Vocabulary Object 6D Pose Estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(2), 2066-2077. https://doi.org/10.1109/tpami.2025.3624589

Vancouver

Corsetti J, Boscaini D, Giuliari F, Oh C, Cavallaro A, Poiesi F. High-Resolution Open-Vocabulary Object 6D Pose Estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(2):2066-2077. doi:10.1109/tpami.2025.3624589

BibTeX
@article{Corsetti2026,
  author = {Corsetti, Jaime and Boscaini, Davide and Giuliari, Francesco and Oh, Changjae and Cavallaro, Andrea and Poiesi, Fabio},
  title = {High-Resolution Open-Vocabulary Object 6D Pose Estimation},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {2},
  pages = {2066--2077},
  doi = {10.1109/tpami.2025.3624589}
}
Kostenlos starten →