提出双流掩码机制，提升点云自编码器的旋转不变性
Beyond Random Masking: A Dual-Stream Approach for Rotation-Invariant Point Cloud Masked Autoencoders
- 结合几何网格与语义聚类，分阶段生成结构化掩码
- 在多个数据集上显著优于传统随机掩码方法
- 可无缝接入现有框架，适合点云表示学习研究者
现有旋转不变点云掩码自编码器依赖随机掩码策略，忽略几何结构与语义一致性。随机掩码独立处理补丁，无法捕捉不同朝向下的空间关系，也忽视旋转下保持身份的语义部件。本文提出双流掩码方法，融合3D空间网格掩码与渐进语义掩码：网格掩码通过坐标排序生成结构化模式，保留跨朝向的几何关系；语义掩码利用注意力聚类发现有意义部件，维持其掩码一致性。两者通过课程学习动态加权协同，从几何理解逐步过渡到语义发现。作为即插即用组件，该方法无需修改架构即可集成至多种旋转不变框架。在ModelNet40、ScanObjectNN和OmniObject3D上的实验表明，在多种旋转场景下均实现显著性能提升。
原文摘要 · Abstract (English)
Existing rotation-invariant point cloud masked autoencoders (MAE) rely on random masking strategies that overlook geometric structure and semantic coherence. Random masking treats patches independently, failing to capture spatial relationships consistent across orientations and overlooking semantic object parts that maintain identity regardless of rotation. We propose a dual-stream masking approach combining 3D Spatial Grid Masking and Progressive Semantic Masking to address these fundamental limitations. Grid masking creates structured patterns through coordinate sorting to capture geometric relationships that persist across different orientations, while semantic masking uses attention-driven clustering to discover semantically meaningful parts and maintain their coherence during masking. These complementary streams are orchestrated via curriculum learning with dynamic weighting, progressing from geometric understanding to semantic discovery. Designed as plug-and-play components, our strategies integrate into existing rotation-invariant frameworks without architectural changes, ensuring broad compatibility across different approaches. Comprehensive experiments on ModelNet40, ScanObjectNN, and OmniObject3D demonstrate consistent improvements across various rotation scenarios, showing substantial performance gains over the baseline rotation-invariant methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。