Point-MoE：通过专家混合实现跨领域泛化的3D语义分割

摘要

尽管缩放定律已经彻底改变了自然语言处理和计算机视觉领域，三维点云理解尚未达到这一阶段。这主要归因于三维数据集的相对较小规模，以及数据来源的多样性。点云由多种传感器（如深度相机、激光雷达）在不同领域（如室内、室外）捕获，每种传感器都引入了独特的扫描模式、采样密度和语义偏差。这种领域异质性对大规模训练统一模型构成了主要障碍，尤其是在推理时通常无法获取领域标签的现实约束下。在本研究中，我们提出了Point-MoE，一种专家混合架构，旨在实现三维感知中的大规模跨领域泛化。我们展示了标准点云骨干网络在混合领域数据上训练时性能显著下降，而采用简单top-k路由策略的Point-MoE即使在没有领域标签的情况下也能自动专业化专家。我们的实验表明，Point-MoE不仅超越了强大的多领域基线，还能更好地泛化到未见过的领域。这项工作为三维理解指明了一条可扩展的前进道路：让模型在多样化的三维数据中发现结构，而非通过人工筛选或领域监督强加结构。

English

While scaling laws have transformed natural language processing and computer vision, 3D point cloud understanding has yet to reach that stage. This can be attributed to both the comparatively smaller scale of 3D datasets, as well as the disparate sources of the data itself. Point clouds are captured by diverse sensors (e.g., depth cameras, LiDAR) across varied domains (e.g., indoor, outdoor), each introducing unique scanning patterns, sampling densities, and semantic biases. Such domain heterogeneity poses a major barrier towards training unified models at scale, especially under the realistic constraint that domain labels are typically inaccessible at inference time. In this work, we propose Point-MoE, a Mixture-of-Experts architecture designed to enable large-scale, cross-domain generalization in 3D perception. We show that standard point cloud backbones degrade significantly in performance when trained on mixed-domain data, whereas Point-MoE with a simple top-k routing strategy can automatically specialize experts, even without access to domain labels. Our experiments demonstrate that Point-MoE not only outperforms strong multi-domain baselines but also generalizes better to unseen domains. This work highlights a scalable path forward for 3D understanding: letting the model discover structure in diverse 3D data, rather than imposing it via manual curation or domain supervision.

Point-MoE：通过专家混合实现跨领域泛化的3D语义分割

Point-MoE: Towards Cross-Domain Generalization in 3D Semantic Segmentation via Mixture-of-Experts

摘要

Summary

Support

Support