PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba Adapter

• URL: http://arxiv.org/abs/2505.20941v1
• Date: Tue, 27 May 2025 09:27:16 GMT
• Title: PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba Adapter
• Authors: Yaohua Zha, Yanzi Wang, Hang Guo, Jinpeng Wang, Tao Dai, Bin Chen, Zhihao Ouyang, Xue Yuerong, Ke Chen, Shu-Tao Xia,
• Abstract summary: We propose Point Mamba Adapter (PMA), which constructs an ordered feature sequence from all layers of the pre-trained model.<n>We also propose a geometry-constrained gate prompt generator (G2PG) shared across different layers.
• Score: 54.33433051500349
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Applying pre-trained models to assist point cloud understanding has recently become a mainstream paradigm in 3D perception. However, existing application strategies are straightforward, utilizing only the final output of the pre-trained model for various task heads. It neglects the rich complementary information in the intermediate layer, thereby failing to fully unlock the potential of pre-trained models. To overcome this limitation, we propose an orthogonal solution: Point Mamba Adapter (PMA), which constructs an ordered feature sequence from all layers of the pre-trained model and leverages Mamba to fuse all complementary semantics, thereby promoting comprehensive point cloud understanding. Constructing this ordered sequence is non-trivial due to the inherent isotropy of 3D space. Therefore, we further propose a geometry-constrained gate prompt generator (G2PG) shared across different layers, which applies shared geometric constraints to the output gates of the Mamba and dynamically optimizes the spatial order, thus enabling more effective integration of multi-layer information. Extensive experiments conducted on challenging point cloud datasets across various tasks demonstrate that our PMA elevates the capability for point cloud understanding to a new level by fusing diverse complementary intermediate features. Code is available at https://github.com/zyh16143998882/PMA.

Related papers

• PointLAMA: Latent Attention meets Mamba for Efficient Point Cloud Pretraining [8.906813021681135]
  Mamba has recently gained widespread attention as a backbone model for point cloud modeling, leveraging a state-space architecture that enables efficient global sequence modeling with linear complexity.<n>We propose textbfPointLAMA, a point cloud pretraining framework that combines task-aware point cloud serialization, a hybrid encoder with integrated Latent Attention and Mamba blocks, and a conditional diffusion mechanism built upon the Mamba backbone.
  arXiv  Detail & Related papers  (2025-07-23T07:57:35Z)
• GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model [14.751171445102626]
  We propose a novel Geometry-Aware Point Cloud Prompt (GAPrompt) to enhance the adaptability of 3D vision models.<n>First, we introduce a Point Prompt that serves as an auxiliary input alongside the original point cloud, explicitly guiding the model to capture fine-grained geometric details.<n>We also present a Point Shift Prompter designed to extract global shape information from the point cloud, enabling instance-specific geometric adjustments at the input level.
  arXiv  Detail & Related papers  (2025-05-07T04:29:09Z)
• NIMBA: Towards Robust and Principled Processing of Point Clouds With SSMs [9.978766637766373]
  We introduce a method to convert point clouds into 1D sequences that maintain 3D spatial structure with no need for data replication. Our method does not require positional embeddings and allows for shorter sequence lengths while still achieving state-of-the-art results.
  arXiv  Detail & Related papers  (2024-10-31T18:58:40Z)
• Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformers [59.0181939916084]
  Traditional 3D networks mainly focus on local geometric details and ignore the topological structure between local geometries. We propose a novel Priors Distillation (RPD) method to extract priors from the well-trained transformers on massive images. Experiments on the PointDA-10 and the Sim-to-Real datasets verify that the proposed method consistently achieves the state-of-the-art performance of UDA for point cloud classification.
  arXiv  Detail & Related papers  (2024-07-26T06:29:09Z)
• 3DMambaComplete: Exploring Structured State Space Model for Point Cloud Completion [19.60626235337542]
  3DMambaComplete is a point cloud completion network built on the novel Mamba framework. It encodes point cloud features using Mamba's selection mechanism and predicts a set of Hyperpoints. A deformation method transforms the 2D mesh representation of HyperPoints into a fine-grained 3D structure for point cloud reconstruction.
  arXiv  Detail & Related papers  (2024-04-10T15:45:03Z)
• Point Cloud Mamba: Point Cloud Learning via State Space Model [73.7454734756626]
  We show that Mamba-based point cloud methods can outperform previous methods based on transformer or multi-layer perceptrons (MLPs) In particular, we demonstrate that Mamba-based point cloud methods can outperform previous methods based on transformer or multi-layer perceptrons (MLPs) Point Cloud Mamba surpasses the state-of-the-art (SOTA) point-based method PointNeXt and achieves new SOTA performance on the ScanNN, ModelNet40, ShapeNetPart, and S3DIS datasets.
  arXiv  Detail & Related papers  (2024-03-01T18:59:03Z)
• PointMamba: A Simple State Space Model for Point Cloud Analysis [65.59944745840866]
  We propose PointMamba, transferring the success of Mamba, a recent representative state space model (SSM), from NLP to point cloud analysis tasks. Unlike traditional Transformers, PointMamba employs a linear complexity algorithm, presenting global modeling capacity while significantly reducing computational costs.
  arXiv  Detail & Related papers  (2024-02-16T14:56:13Z)
• PointPatchMix: Point Cloud Mixing with Patch Scoring [58.58535918705736]
  We propose PointPatchMix, which mixes point clouds at the patch level and generates content-based targets for mixed point clouds. Our approach preserves local features at the patch level, while the patch scoring module assigns targets based on the content-based significance score from a pre-trained teacher model. With Point-MAE as our baseline, our model surpasses previous methods by a significant margin, achieving 86.3% accuracy on ScanObjectNN and 94.1% accuracy on ModelNet40.
  arXiv  Detail & Related papers  (2023-03-12T14:49:42Z)
• AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformers [94.11915008006483]
  We present a new method that reformulates point cloud completion as a set-to-set translation problem. We design a new model, called PoinTr, which adopts a Transformer encoder-decoder architecture for point cloud completion. Our method attains 6.53 CD on PCN, 0.81 CD on ShapeNet-55 and 0.392 MMD on real-world KITTI.
  arXiv  Detail & Related papers  (2023-01-11T16:14:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.