ORE-Mamba: Objective-Driven Representation Evolution with Mamba for Point Cloud Analysis
Sensors · 09.11.2026 · 26 (21) · 7071
DOI: 10.3390/s26217071 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 09.11.2026. Verfasst von Yuan Huang und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Information and Artificial Intelligence, Yangzhou University, Yangzhou 225127, China. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Point clouds are a fundamental sensing modality for object perception, scene understanding, and robotic interaction in modern three-dimensional sensing systems. Effective point-cloud understanding requires representations that preserve intrinsic geometric structure while progressively emphasizing task-discriminative information. However, existing Point Mamba architectures typically encode these heterogeneous requirements in a unified token state that evolves along a shared state-space trajectory, potentially limiting functional specialization and complementarity. To address this limitation, we propose ORE-Mamba, an objective-driven representation evolution framework that organizes feature transformations according to their intended functional roles. Here, objective-driven refers to the functional purpose assigned to a representation pathway rather than to an additional training objective or auxiliary loss. ORE-Mamba maintains geometry-oriented and saliency-oriented representations in two distinct but collaborative streams. The geometry stream employs Local Geometry Aggregation Mamba (LGAM) to encode Euclidean neighborhood relations and propagate geometry-aware information over long ranges through a projected-channel bidirectional state-space model (Bi-SSM). The saliency stream employs Receptive-Field Coordinate Attention (RFCA), which combines Morton Z-order serialization with receptive-field-aware position–channel recalibration to selectively enhance task-relevant responses. Stage-wise bidirectional residual interaction exchanges complementary information between the two streams, while token-wise gated fusion adaptively integrates their final representations. Experiments on ModelNet40, ScanObjectNN, and ShapeNetPart demonstrate strong performance in object classification, part segmentation, and few-shot recognition. Without pre-training, ORE-Mamba achieves mean accuracies of 94.0% on ModelNet40 and 95.24%, 94.03%, and 92.11% on the OBJ-BG, OBJ-ONLY, and PB-T50-RS variants of ScanObjectNN, respectively, across three independent training runs. With 15.7 M parameters and 4.7 G FLOPs, ORE-Mamba provides a favorable trade-off between representational capacity and computational cost. These results support objective-driven representation evolution as an effective alternative to unified feature propagation for point-cloud learning.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Information and Artificial Intelligence, Yangzhou University, Yangzhou 225127, China.
ORCID-Profile: Yuan Huang, Shuhan Chen
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Huang, Y., Wang, X., Zhang, J., Chen, S., & Zhao, Y. (2026). ORE-Mamba: Objective-Driven Representation Evolution with Mamba for Point Cloud Analysis. Sensors, 26(21), 7071. https://doi.org/10.3390/s26217071
Vancouver
Huang Y, Wang X, Zhang J, Chen S, Zhao Y. ORE-Mamba: Objective-Driven Representation Evolution with Mamba for Point Cloud Analysis. Sensors. 2026;26(21):7071. doi:10.3390/s26217071
BibTeX
@article{Huang2026,
author = {Huang, Yuan and Wang, Xiaoyang and Zhang, Jiayu and Chen, Shuhan and Zhao, Yu},
title = {ORE-Mamba: Objective-Driven Representation Evolution with Mamba for Point Cloud Analysis},
journal = {Sensors},
year = {2026},
volume = {26},
number = {21},
pages = {7071},
doi = {10.3390/s26217071}
}
EUVIMED