CNOS: A Strong Baseline for CAD-based Novel Object Segmentation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

CNOS: A Strong Baseline for CAD-based Novel Object Segmentation

van Nguyen Nguyen
Thibault Groueix
  • Fonction : Auteur
Tomas Hodan
  • Fonction : Auteur

Résumé

We propose a simple three-stage approach to segment unseen objects in RGB images using their CAD models. Leveraging recent powerful foundation models, DINOv2 and Segment Anything, we create descriptors and generate proposals, including binary masks for a given input RGB image. By matching proposals with reference descriptors created from CAD models, we achieve precise object ID assignment along with modal masks. We experimentally demonstrate that our method achieves state-of-the-art results in CAD-based novel object segmentation, surpassing existing approaches on the seven core datasets of the BOP challenge by 19.8% AP using the same BOP evaluation protocol. Our source code is available at https://github.com/nv-nguyen/cnos.
Fichier non déposé

Dates et versions

hal-04324317 , version 1 (05-12-2023)

Identifiants

Citer

van Nguyen Nguyen, Thibault Groueix, Georgy Ponimatkin, Vincent Lepetit, Tomas Hodan. CNOS: A Strong Baseline for CAD-based Novel Object Segmentation. Proceedings of the IEEE/CVF International Conference on Computer Vision, Oct 2023, Paris, France. ⟨10.48550/arXiv.2307.11067⟩. ⟨hal-04324317⟩
29 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More