DAPointMamba: Domain Adaptive Point Mamba for Point Cloud Completion

2025-11-25

AI Summary

This work addresses geometric structure mismatch and semantic discrepancy between source and target domains in domain-adaptive point cloud completion (DA-PCC). We propose the first lightweight, efficient framework based on state space models (SSMs). Methodologically, we introduce a cross-domain block-level serialization scanning strategy, coupled with a spatial-channel dual-dimension SSM alignment mechanism that preserves local geometric fidelity while mitigating fine-grained structural discrepancies and global semantic shifts. Additionally, we design a channel-interleaved alignment technique to achieve linear-time complexity and low inference latency. Extensive experiments on both synthetic and real-world datasets demonstrate that our method significantly outperforms existing state-of-the-art approaches in completion accuracy and domain adaptation capability, while simultaneously reducing computational overhead and inference delay.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Diffusion Models for Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

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.

Problem

• Addressing geometric and semantic gaps in domain adaptive point cloud completion
• Overcoming limited receptive fields and quadratic complexity in existing methods
• Enhancing cross-domain spatial consistency and global semantic alignment

Innovation

• Uses State Space Models for domain adaptation
• Introduces Cross-Domain Patch-Level Scanning
• Implements Spatial and Channel SSM Alignment