Point-MoE：通過專家混合實現3D語義分割的跨領域泛化

摘要

儘管縮放定律已經革新了自然語言處理和計算機視覺領域，三維點雲理解尚未達到這一階段。這可歸因於三維數據集的相對較小規模，以及數據本身來源的多樣性。點雲由多種傳感器（如深度相機、LiDAR）在不同領域（如室內、室外）捕捉，每種傳感器都引入了獨特的掃描模式、採樣密度和語義偏差。這種領域異質性對大規模訓練統一模型構成了主要障礙，特別是在推理時通常無法獲取領域標籤的現實約束下。在本研究中，我們提出了Point-MoE，一種專家混合架構，旨在實現三維感知中的大規模跨領域泛化。我們展示了標準點雲骨幹在混合領域數據上訓練時性能顯著下降，而採用簡單的top-k路由策略的Point-MoE能夠自動專精化專家，即使無需訪問領域標籤。我們的實驗表明，Point-MoE不僅超越了強大的多領域基線，還能更好地泛化到未見領域。這項工作為三維理解指明了一條可擴展的前進道路：讓模型在多樣的三維數據中發現結構，而非通過人工整理或領域監督強加結構。

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：通過專家混合實現3D語義分割的跨領域泛化

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

摘要

Support