无需训练，用测试数据动态更新知识库，让3D点云模型识别新类别。
Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud Analysis
- 构建分层缓存，记录测试样本的全局结构与局部细节特征。
- 在8个基准上提升性能，支持识别训练时未见的新类别。
- 零训练开销，可插件式接入主流3D模型，适合在线推理场景。
本文提出一种通用方案，使点云识别模型能在测试阶段应对分布偏移。不同于依赖训练数据且仅限于预定义类别的方法，我们探索更贴近实际的挑战：仅基于在线测试数据，实现对已见类别和未见新类别的识别。为此，我们设计了 extbf{Point-Cache}，一个分层缓存模型，能捕捉测试样本的关键信息，尤其关注点云的全局结构与局部细节。该缓存作为丰富的3D知识库，动态管理以优先保留高质量样本。作为即插即用模块，可灵活集成至大型多模态3D模型中，支持开放词汇点云识别。其效率与零样本推理相当，完全无需训练。Point-Cache 在8个挑战性基准和4个代表性大3D模型上均取得显著提升，验证了有效性。代码已开源：https://github.com/auniquesun/Point-Cache。
原文摘要 · Abstract (English)
This paper proposes a general solution to enable point cloud recognition models to handle distribution shifts at test time. Unlike prior methods, which rely heavily on training data (often inaccessible during online inference) and are limited to recognizing a fixed set of point cloud classes predefined during training, we explore a more practical and challenging scenario: adapting the model solely based on online test data to recognize both previously seen classes and novel, unseen classes at test time. To this end, we develop \textbf{Point-Cache}, a hierarchical cache model that captures essential clues of online test samples, particularly focusing on the global structure of point clouds and their local-part details. Point-Cache, which serves as a rich 3D knowledge base, is dynamically managed to prioritize the inclusion of high-quality samples. Designed as a plug-and-play module, our method can be flexibly integrated into large multimodal 3D models to support open-vocabulary point cloud recognition. Notably, our solution operates with efficiency comparable to zero-shot inference, as it is entirely training-free. Point-Cache demonstrates substantial gains across 8 challenging benchmarks and 4 representative large 3D models, highlighting its effectiveness. Code is available at https://github.com/auniquesun/Point-Cache.
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。