MANBO: Mamba-Based Lightweight Attention Network with Priority-Bridged Ordering for Point Cloud Processing
- 1Graduate School of Automobile and Mobility, Kookmin University, Seoul 02707, Republic of Korea
- 2Department of Automobile and IT Convergence, Kookmin University, Seoul 02707, Republic of Korea
Abstract
Selective state space models (SSMs) enable efficient long-range dependency modeling across language, vision, and 3D domains. However, because SSMs are optimized for sequential processing, they handle spatially irregular inputs such as point clouds poorly. We propose MANBO, which couples a graph-based node priority selection mechanism with the Mamba block to model long-range context while preserving local relational structure. A lightweight graph network learns semantic relations among point patches and derives a priority score for each patch from the concentration of its local attention. A priority–space integration strategy then orders patches by both spatial proximity and the attention-derived priority, and we extend the reconstruction scope of masked pre-training to couple global contextual learning with fine-grained local reconstruction. On ScanObjectNN, ModelNet40, and ShapeNetPart, MANBO achieves 94.76% (OBJ-BG), 93.2%, and 86.3 mIoU, respectively, with consistent improvements over Mamba-based baselines. These results indicate that jointly addressing serialization and representation learning is an effective way to apply SSMs to object-level point cloud understanding.
Related
- The journey of numbers from attention to motor processing: an embodied account of neural response to number magnitudes.
- A parallel convolution attention network for crop genomic prediction
- A prototype-aligned multi-scale attention network for few-shot industrial surface defect detection
- Response Time Stochastic Analysis for Fixed-Priority Stable Real-Time Systems
- Well-Posedness and Asymptotic Behavior of the Standby Repairable System with Partial Failure and Priority
BibTeX
@article{kim2026manbo,
title = {{MANBO: Mamba-Based Lightweight Attention Network with Priority-Bridged Ordering for Point Cloud Processing}},
author = {Jaehyeok Kim and Jumyung Kim and Jinwoo Yoo},
journal = {Mathematics},
year = {2026},
month = oct,
doi = {10.3390/math14193635},
url = {https://www.mdpi.com/2227-7390/14/19/3635},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - MANBO: Mamba-Based Lightweight Attention Network with Priority-Bridged Ordering for Point Cloud Processing
AU - Jaehyeok Kim
AU - Jumyung Kim
AU - Jinwoo Yoo
PY - 2026
DA - 2026/10/08
JO - Mathematics
DO - 10.3390/math14193635
UR - https://www.mdpi.com/2227-7390/14/19/3635
AB - Selective state space models (SSMs) enable efficient long-range dependency modeling across language, vision, and 3D domains. However, because SSMs are optimized for sequential processing, they handle spatially irregular inputs such as point clouds poorly. We propose MANBO, which couples a graph-based node priority selection mechanism with the Mamba block to model long-range context while preserving local relational structure. A lightweight graph network learns semantic relations among point patches and derives a priority score for each patch from the concentration of its local attention. A priority–space integration strategy then orders patches by both spatial proximity and the attention-derived priority, and we extend the reconstruction scope of masked pre-training to couple global contextual learning with fine-grained local reconstruction. On ScanObjectNN, ModelNet40, and ShapeNetPart, MANBO achieves 94.76% (OBJ-BG), 93.2%, and 86.3 mIoU, respectively, with consistent improvements over Mamba-based baselines. These results indicate that jointly addressing serialization and representation learning is an effective way to apply SSMs to object-level point cloud understanding.
SN - 2227-7390
ER -