BPNet: Bézier Primitive Segmentation on 3D Point Clouds - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

BPNet: Bézier Primitive Segmentation on 3D Point Clouds

BPNet: Bézier Primitive Segmentation on 3D Point Clouds

Rao Fu
  • Fonction : Auteur
  • PersonId : 1267714
Xiao Xiao
  • Fonction : Auteur
  • PersonId : 1267716
Pierre Alliez

Résumé

This paper proposes BPNet, a novel end-to-end deep learning framework to learn Bézier primitive segmentation on 3D point clouds. The existing works treat different primitive types separately, thus limiting them to finite shape categories. To address this issue, we seek a generalized primitive segmentation on point clouds. Taking inspiration from Bézier decomposition on NURBS models, we transfer it to guide point cloud segmentation casting off primitive types. A joint optimization framework is proposed to learn Bézier primitive segmentation and geometric fitting simultaneously on a cascaded architecture. Specifically, we introduce a soft voting regularizer to improve primitive segmentation and propose an auto-weight embedding module to cluster point features, making the network more robust and generic. We also introduce a reconstruction module where we successfully process multiple CAD models with different primitives simultaneously. We conducted extensive experiments on the synthetic ABC dataset and real-scan datasets to validate and compare our approach with different baseline methods. Experiments show superior performance over previous work in terms of segmentation, with a substantially faster inference speed.
Fichier principal
Vignette du fichier
BPNet.pdf (3.68 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

ineris-04151504 , version 1 (05-07-2023)

Licence

Paternité

Identifiants

Citer

Rao Fu, Cheng Wen, Qian Li, Xiao Xiao, Pierre Alliez. BPNet: Bézier Primitive Segmentation on 3D Point Clouds. IJCAI 2023 - 32nd International Joint Conference on Artificial Intelligence, Aug 2023, MACAO, Macau SAR China. pp.1-9, ⟨10.24963/ijcai.2023/84⟩. ⟨ineris-04151504⟩
127 Consultations
103 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More