让3D场景支持多粒度文本搜索，可查零件、物体或材质区域
Search3D: Hierarchical Open-Vocabulary 3D Segmentation
- 构建分层开放词汇3D表示，支持从零件到材质的多级文本检索
- 在MultiScan和ScanNet++上实现领先性能，尤其在细粒度部件分割上
- 适合需要灵活3D语义搜索的科研与工业应用
开放词汇3D分割使用户能用自由文本描述探索3D空间。现有方法主要聚焦物体级实例识别，难以处理如物体部件或通用属性描述的细粒度场景实体。本文提出Search3D，构建分层开放词汇3D场景表示，支持多粒度3D搜索：细粒度部件、完整物体或由材质等属性描述的区域。不同于以往以物体为中心的查询方式，Search3D采用更灵活的开放词汇搜索范式。为系统评估，我们基于MultiScan构建了场景级开放词汇3D部件分割基准，并在ScanNet++上提供一组开放词汇细粒度部件标注。Search3D在场景级开放词汇3D部件分割任务中优于基线，同时保持对3D物体和材料分割的强性能。
原文摘要 · Abstract (English)
Open-vocabulary 3D segmentation enables exploration of 3D spaces using free-form text descriptions. Existing methods for open-vocabulary 3D instance segmentation primarily focus on identifying object-level instances but struggle with finer-grained scene entities such as object parts, or regions described by generic attributes. In this work, we introduce Search3D, an approach to construct hierarchical open-vocabulary 3D scene representations, enabling 3D search at multiple levels of granularity: fine-grained object parts, entire objects, or regions described by attributes like materials. Unlike prior methods, Search3D shifts towards a more flexible open-vocabulary 3D search paradigm, moving beyond explicit object-centric queries. For systematic evaluation, we further contribute a scene-scale open-vocabulary 3D part segmentation benchmark based on MultiScan, along with a set of open-vocabulary fine-grained part annotations on ScanNet++. Search3D outperforms baselines in scene-scale open-vocabulary 3D part segmentation, while maintaining strong performance in segmenting 3D objects and materials. Our project page is http://search3d-segmentation.github.io.
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。