EUVIMEDEUVIMED entdecken
Crossref

Reliable-View 2D-3D Key-Part Aligned Transformer with Reinforced Masking for 3D Point Cloud Understanding

Xianglong Jin, Zheng Wang, Rong Wang, Feiping Nie

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (7) · 5530-5538

DOI: 10.1609/aaai.v40i7.37471 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Xianglong Jin und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Self-supervised 3D point cloud understanding is crucial for scene understanding, where Masked Autoencoders (MAE) have achieved excellent performance in point cloud representation learning. However, existing MAE-style methods fail to consider spatial-semantic variations in masking strategies, and joint learning with multi-view images often overlooks view redundancy. To address these challenges, we propose an MAE framework enhanced with reliable multi-view 2D-3D Key-part alignment and Reinforced masking, named as KR-MAE. Our approach comprises three key innovations: Reinforced Masking (RM) strategically samples visible tokens based on semantic saliency to enhance reconstruction fidelity; Reliable Multi-View Selector (RVS) dynamically refines the most informative image subset by filtering occluded or low-texture views, mitigating detrimental redundancy; Reliable-view 2D-3D Key-part Aligned Transformer (KAT) establishes semantic-aligned correspondence between salient 3D point cloud parts and reliable multi-view 2D image patches, leveraging rich texture cues from 2D images to compensate for sparse geometry in point cloud. Extensive experiments on 3D classification and segmentation benchmarks demonstrate that KR-MAE achieves state-of-the-art performance, surpassing prior multi-modal methods.

Zitieren

APA

Jin, X., Wang, Z., Wang, R., & Nie, F. (2026). Reliable-View 2D-3D Key-Part Aligned Transformer with Reinforced Masking for 3D Point Cloud Understanding. Proceedings of the AAAI Conference on Artificial Intelligence, 40(7), 5530-5538. https://doi.org/10.1609/aaai.v40i7.37471

Vancouver

Jin X, Wang Z, Wang R, Nie F. Reliable-View 2D-3D Key-Part Aligned Transformer with Reinforced Masking for 3D Point Cloud Understanding. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(7):5530-5538. doi:10.1609/aaai.v40i7.37471

BibTeX
@article{Jin2026,
  author = {Jin, Xianglong and Wang, Zheng and Wang, Rong and Nie, Feiping},
  title = {Reliable-View 2D-3D Key-Part Aligned Transformer with Reinforced Masking for 3D Point Cloud Understanding},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {7},
  pages = {5530--5538},
  doi = {10.1609/aaai.v40i7.37471}
}
Kostenlos starten →