COSTA: A Cluster-Centric Paradigm for Annotation-Free Open-Set Semantic Segmentation of Aerial Point Clouds with Domain Shifts

📄 arXiv: 2608.18479v1 📥 PDF

作者: Yanghong Lin, Li Fang, Tianyu Li, Shudong Zhou, Wei Yao

分类: cs.CV

发布日期: 2026-08-19

💡 一句话要点

提出COSTA以解决航空点云开放集语义分割问题

🎯 匹配领域: 支柱三：空间感知与语义 (Perception & Semantics)

关键词: 航空点云 语义分割 开放集学习 领域转移 集群中心 测试阶段适应 视觉-语言模型

📋 核心要点

  1. 现有的航空点云语义分割方法在领域转移下面临泛化危机，难以适应未标注的目标领域数据。
  2. COSTA通过集群中心的开放集语义传播，提出了一种新的测试阶段适应方法，突破了封闭集标签的限制。
  3. 在DALES源领域的基础上，COSTA在三个具有不同领域和类别空间的航空点云基准上实现了显著的性能提升。

📝 摘要（中文）

航空点云的语义分割在不同领域转移下面临泛化危机。现有方法受限于封闭集标签假设和不可扩展的逐点分割管道，难以应对语义转移。本文提出COSTA，通过从封闭集逐点适应转向集群中心开放集语义传播，解决了这一限制。COSTA在测试阶段有效适应后，将航空点云的丰富特征分布提炼为可跨标签空间转移的紧凑语义中心集，从而实现开放集语义分割。实验结果表明，COSTA在不同领域和异构类别空间的三个航空点云基准上，达到了最高70.09%的mIoU。

🔬 方法详解

问题定义：本文旨在解决航空点云在领域转移下的开放集语义分割问题。现有方法受限于封闭集标签假设，无法有效适应未标注的目标领域数据。

核心思路：COSTA的核心思路是通过集群中心的开放集语义传播，利用测试阶段的适应性，将特征分布提炼为可转移的语义中心，从而实现对目标领域的有效分割。

技术框架：COSTA的整体架构包括三个主要模块：首先，通过测试阶段适应缩小领域差距；其次，将目标领域点云根据适应后的特征空间相似性分组为语义集群；最后，通过集群投票将高置信度伪标签传播到所有点。

关键创新：COSTA的主要创新在于将语义分割问题从逐点适应转变为集群中心的开放集传播，显著提升了在领域转移下的适应能力。

关键设计：在设计中，COSTA采用了基于相似性分布的集群划分策略，并结合开放词汇视觉-语言模型进行伪标签生成，确保了标签的高置信度和准确性。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

COSTA在三个航空点云基准上实现了最高70.09%的mIoU，相较于现有方法显著提升了性能，尤其在处理具有显著领域差距和混合语义转移的情况下，展现了其优越性。

🎯 应用场景

COSTA的研究成果在航空遥感、环境监测和城市规划等领域具有广泛的应用潜力。通过实现开放集语义分割，该方法能够在不同的领域和类别空间中灵活适应，提升数据处理的效率和准确性，推动相关领域的智能化发展。

📄 摘要（原文）

Semantic segmentation of aerial point cloud is trapped in a generalization crisis under distinct domain shifts. While test-time adaptation offers a privacy-preserving and computationally efficient way to adapt pre-trained models to unlabeled target-domain data during inference, existing methods, bound to closed-set label assumptions and non-scalable point-wise segmentation pipelines, still struggle with semantic shifts. We ask: can we adapt any given pre-trained aerial point cloud segmentation model to a shifted target domain at the inference phase alone, without additional training, while segmenting target-specific categories beyond the source label space on demand? This paper introduces COSTA, which breaks this limitation by shifting from closed-set point-wise adaptation to cluster-centric open-set semantic propagation. Our core discovery is that, once effectively adapted at test time, the rich feature distribution of aerial point clouds can be distilled into a compact set of well-separated semantic centroids that are transferable across label spaces. COSTA leverages this to reformulate open-set semantic segmentation as a cluster-level propagating process: it first bridges the domain gap through proven test-time adaptation, then groups each batch of target-domain points into a small set of semantic clusters based on the similarity distribution in the adapted feature space, and finally propagates high-confidence pseudo labels obtained from an open-vocabulary vision-language model to all points through cluster-level voting. This cluster-centric paradigm enables test-time adaptation of aerial point clouds under significant domain gaps with mixed semantic shifts. With DALES as the source domain, COSTA enables on-demand segmentation across three aerial point cloud benchmarks with distinct domains and heterogeneous category spaces, achieving up to 70.09% mIoU under this new setting.