用Transformer加速3D点云检索，实现毫秒级匹配。
Fast 3D point clouds retrieval for Large-scale 3D Place Recognition
- 将文本检索的可微索引迁移到3D点云，生成1D标识符
- 在公开数据集上达到顶尖检索精度，速度提升数十倍
- 适合大规模3D场景识别与实时应用
3D点云检索是一项挑战性任务，旨在从参考点云库中找出与查询点云最相似的若干个。现有方法主要依赖点云描述符的对比来识别相似项。由于该步骤复杂度高，本文聚焦于通过改进可微搜索索引（DSI）来加速检索过程。DSI是一种最初用于文本信息检索的基于Transformer的方法，我们将其适配到3D点云场景：生成基于点描述符的1维标识符，实现常数时间直接检索。为适配3D数据，引入视觉变换器（Vision Transformer）将描述符映射为标识符，并融合位置与语义编码。在公开基准上的实验表明，该方法在点云检索的质量与速度方面均优于当前最优方法。
原文摘要 · Abstract (English)
Retrieval in 3D point clouds is a challenging task that consists in retrieving the most similar point clouds to a given query within a reference of 3D points. Current methods focus on comparing descriptors of point clouds in order to identify similar ones. Due to the complexity of this latter step, here we focus on the acceleration of the retrieval by adapting the Differentiable Search Index (DSI), a transformer-based approach initially designed for text information retrieval, for 3D point clouds retrieval. Our approach generates 1D identifiers based on the point descriptors, enabling direct retrieval in constant time. To adapt DSI to 3D data, we integrate Vision Transformers to map descriptors to these identifiers while incorporating positional and semantic encoding. The approach is evaluated for place recognition on a public benchmark comparing its retrieval capabilities against state-of-the-art methods, in terms of quality and speed of returned point clouds.
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。