Scalable 3D Panoptic Segmentation With Superpoint Graph Clustering
In: 11th International Conference on 3D Vision 2024 (3DV 2024) ; https://hal.science/hal-04398319 ; 11th International Conference on 3D Vision 2024 (3DV 2024), Mar 2024, Davos, Switzerland ; https://3dvconf.github.io/2024/, 2024
Online
Konferenz
Zugriff:
Accepted at 3DV 2024, Oral presentation ; International audience ; We introduce a highly efficient method for panoptic segmentation of large 3D point clouds by redefining this taskas 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.
Titel: |
Scalable 3D Panoptic Segmentation With Superpoint Graph Clustering
|
---|---|
Autor/in / Beteiligte Person: | Robert, Damien ; Raguet, Hugo ; Landrieu, Loic ; Laboratoire sciences et technologies de l'information géographique (LaSTIG) ; Ecole des Ingénieurs de la Ville de Paris (EIVP)-École nationale des sciences géographiques (ENSG) ; Institut National de l'Information Géographique et Forestière IGN (IGN)-Université Gustave Eiffel-Institut National de l'Information Géographique et Forestière IGN (IGN)-Université Gustave Eiffel ; Laboratoire d'Informatique Fondamentale et Appliquée de Tours (LIFAT) ; Université de Tours (UT)-Institut National des Sciences Appliquées - Centre Val de Loire (INSA CVL) ; Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS) ; Laboratoire d'Informatique Gaspard-Monge (LIGM) ; École des Ponts ParisTech (ENPC)-Centre National de la Recherche Scientifique (CNRS)-Université Gustave Eiffel ; ENGIE Lab, CRIGEN ; GENCI–IDRIS (Grant 2023-AD011013388R1) ; ANR-19-CE23-0007,READY3D,Analyse tempts-réel de nuages de points LiDAR dynamiques(2019) |
Link: | |
Zeitschrift: | 11th International Conference on 3D Vision 2024 (3DV 2024) ; https://hal.science/hal-04398319 ; 11th International Conference on 3D Vision 2024 (3DV 2024), Mar 2024, Davos, Switzerland ; https://3dvconf.github.io/2024/, 2024 |
Veröffentlichung: | HAL CCSD, 2024 |
Medientyp: | Konferenz |
Schlagwort: |
|
Sonstiges: |
|