EUVIMEDEUVIMED entdecken
Crossref

Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation of Indoor Scenes

Zeyu Hu, Xuyang Bai, Jiaxiang Shang, Runze Zhang, Jiayu Dong, Xin Wang, Guangyuan Sun, Hongbo Fu, Chiew-Lan Tai

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-05 · 47 (5) · 3244-3256

DOI: 10.1109/tpami.2022.3194555 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-05. Verfasst von Zeyu Hu und 8 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 74 Literaturangaben. Gefördert von: City University of Hong Kong.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, sparse voxel-based methods have become the state-of-the-arts for 3D semantic segmentation of indoor scenes, thanks to the powerful 3D CNNs. Nevertheless, being oblivious to the underlying geometry, voxel-based methods suffer from ambiguous features on spatially close objects and struggle with handling complex and irregular geometries due to the lack of geodesic information. In view of this, we present Voxel-Mesh Network (VMNet), a novel 3D deep architecture that operates on the voxel and mesh representations leveraging both the euclidean and geodesic information. Intuitively, the euclidean information extracted from voxels can offer contextual cues representing interactions between nearby objects, while the geodesic information extracted from meshes can help separate objects that are spatially close but have disconnected surfaces. To incorporate such information from the two domains, we design an intra-domain attentive module for effective feature aggregation and an inter-domain attentive module for adaptive feature fusion. Experimental results validate the effectiveness of VMNet: specifically, on the challenging ScanNet dataset for large-scale segmentation of indoor scenes, it outperforms the state-of-the-art SparseConvNet and MinkowskiNet (74.6% versus 72.5% and 73.6% in mIoU) with a simpler network structure (17M versus 30M and 38M parameters).

Förderung

  • City University of Hong Kong

Zitieren

APA

Hu, Z., Bai, X., Shang, J., Zhang, R., Dong, J., Wang, X., Sun, G., Fu, H., & Tai, C. L. (2025). Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation of Indoor Scenes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(5), 3244-3256. https://doi.org/10.1109/tpami.2022.3194555

Vancouver

Hu Z, Bai X, Shang J, Zhang R, Dong J, Wang X, et al. Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation of Indoor Scenes. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(5):3244-3256. doi:10.1109/tpami.2022.3194555

BibTeX
@article{Hu2025,
  author = {Hu, Zeyu and Bai, Xuyang and Shang, Jiaxiang and Zhang, Runze and Dong, Jiayu and Wang, Xin and Sun, Guangyuan and Fu, Hongbo and Tai, Chiew-Lan},
  title = {Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation of Indoor Scenes},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {5},
  pages = {3244--3256},
  doi = {10.1109/tpami.2022.3194555}
}
Kostenlos starten →