DAPointMamba: Domain Adaptive Point Mamba for Point Cloud Completion
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (8) · 6653-6661
DOI: 10.1609/aaai.v40i8.37596 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yinghui Li und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Domain adaptive point cloud completion (DA PCC) aims to narrow the geometric and semantic discrepancies between the labeled source and unlabeled target domains. Existing methods either suffer from limited receptive fields or quadratic complexity due to using CNNs or vision Transformers. In this paper, we present the first work that studies the adaptability of state space models (SSMs) in DA PCC and find that directly applying SSMs to DA PCC will encounter several challenges: directly serializing 3D point clouds into 1D sequences often disrupts the spatial topology and local geometric features of the target domain. Besides, the overlook of designs in the learning domain-agnostic representations hinders the adaptation performance. To address these issues, we propose a novel framework, DAPointMamba for DA PCC, that exhibits strong adaptability across domains and has the advantages of global receptive fields and efficient linear complexity. It has three novel modules. In particular, Cross-Domain Patch-Level Scanning introduces patch-level geometric correspondences, enabling effective local alignment. Cross-Domain Spatial SSM Alignment further strengthens spatial consistency by modulating patch features based on cross-domain similarity, effectively mitigating fine-grained structural discrepancies. Cross-Domain Channel SSM Alignment actively addresses global semantic gaps by interleaving and aligning feature channels. Extensive experiments on both synthetic and real-world benchmarks demonstrate that our DAPointMamba outperforms state-of-the-art methods with less computational complexity and inference latency.
Zitieren
APA
Li, Y., Zhou, Q., Shao, D., Yang, H., Zhu, Y., Dazeley, R., & Lu, X. (2026). DAPointMamba: Domain Adaptive Point Mamba for Point Cloud Completion. Proceedings of the AAAI Conference on Artificial Intelligence, 40(8), 6653-6661. https://doi.org/10.1609/aaai.v40i8.37596
Vancouver
Li Y, Zhou Q, Shao D, Yang H, Zhu Y, Dazeley R, et al. DAPointMamba: Domain Adaptive Point Mamba for Point Cloud Completion. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(8):6653-6661. doi:10.1609/aaai.v40i8.37596
BibTeX
@article{Li2026,
author = {Li, Yinghui and Zhou, Qianyu and Shao, Di and Yang, Hao and Zhu, Ye and Dazeley, Richard and Lu, Xuequan},
title = {DAPointMamba: Domain Adaptive Point Mamba for Point Cloud Completion},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {8},
pages = {6653--6661},
doi = {10.1609/aaai.v40i8.37596}
}
EUVIMED