Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering

Résumé

We introduce a highly efficient method for panoptic segmentation of large 3D point clouds by redefining this task as a scalable graph clustering problem. This approach can be trained using only local auxiliary tasks, thereby eliminating the resource-intensive instance-matching step during training. Moreover, our formulation can easily be adapted to the superpoint paradigm, further increasing its efficiency. This allows our model to process scenes with millions of points and thousands of objects in a single inference. Our method, called SuperCluster, achieves a new state-of-the-art panoptic segmentation performance for two indoor scanning datasets: 50.1 PQ (+7.8) for S3DIS Area 5, and 58.7 PQ (+25.2) for ScanNetV2. We also set the first state-of-the-art for two large-scale mobile mapping benchmarks: KITTI-360 and DALES. With only 209k parameters, our model is over 30 times smaller than the best-competing method and trains up to 15 times faster. Our code and pretrained models are available at https://github.com/drprojects/superpoint_transformer.
Fichier principal
Vignette du fichier
3dv_2024_supercluster.pdf (6.3 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04398319 , version 1 (16-01-2024)
hal-04398319 , version 2 (09-02-2024)

Licence

Paternité

Identifiants

Citer

Damien Robert, Hugo Raguet, Loic Landrieu. Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering. 11th International Conference on 3D Vision 2024 (3DV 2024), Mar 2024, Davos, Switzerland. ⟨hal-04398319v2⟩
52 Consultations
8 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More