Score: 1

DM3D: Deformable Mamba via Offset-Guided Gaussian Sequencing for Point Cloud Understanding

Published: December 3, 2025 | arXiv ID: 2512.03424v1

By: Bin Liu, Chunyang Wang, Xuelian Liu

Potential Business Impact:

Helps computers understand 3D shapes better.

Business Areas:
3D Printing Manufacturing

State Space Models (SSMs) demonstrate significant potential for long-sequence modeling, but their reliance on input order conflicts with the irregular nature of point clouds. Existing approaches often rely on predefined serialization strategies, which cannot adjust based on diverse geometric structures. To overcome this limitation, we propose \textbf{DM3D}, a deformable Mamba architecture for point cloud understanding. Specifically, DM3D introduces an offset-guided Gaussian sequencing mechanism that unifies local resampling and global reordering within a deformable scan. The Gaussian-based KNN Resampling (GKR) enhances structural awareness by adaptively reorganizing neighboring points, while the Gaussian-based Differentiable Reordering (GDR) enables end-to-end optimization of serialization order. Furthermore, a Tri-Path Frequency Fusion module enhances feature complementarity and reduces aliasing. Together, these components enable structure-adaptive serialization of point clouds. Extensive experiments on benchmark datasets show that DM3D achieves state-of-the-art performance in classification, few-shot learning, and part segmentation, demonstrating that adaptive serialization effectively unlocks the potential of SSMs for point cloud understanding.

Page Count
10 pages

Category
Computer Science:
CV and Pattern Recognition