构建首个高精度纹理化3D部件数据集，助力细粒度物体理解
PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding
- 基于23000个带纹理3D模型，实现50类物体的层级化部件标注
- 在细粒度分割和3D视觉问答任务上，显著超越现有方法表现
- 适合做3D结构理解、多模态大模型、机器人抓取等研究者使用
理解物体的组成部分是推动计算机视觉、图形学与机器人技术发展的基础。尽管已有如PartNet的数据集推动了3D部件理解进展，但其依赖无纹理几何形状且需专家标注，限制了可扩展性与实用性。本文提出PartNeXt，一个下一代数据集，包含超过23,000个高质量、带纹理的3D模型，覆盖50个类别，具备细粒度、层级化的部件标签。我们在两个任务上对PartNeXt进行基准测试：(1) 类无关部件分割，当前顶尖方法（如PartField、SAMPart3D）在细粒度及叶级部件上表现不佳；(2) 面向3D-LLMs的部件中心问答任务，揭示了开放词汇部件定位的重大差距。此外，在PartNeXt上训练Point-SAM相比在PartNet上取得显著提升，证明其质量与多样性更优。通过可扩展标注、纹理感知标签与多任务评估，PartNeXt为结构化3D理解研究开辟新路径。
原文摘要 · Abstract (English)
Understanding objects at the level of their constituent parts is fundamental to advancing computer vision, graphics, and robotics. While datasets like PartNet have driven progress in 3D part understanding, their reliance on untextured geometries and expert-dependent annotation limits scalability and usability. We introduce PartNeXt, a next-generation dataset addressing these gaps with over 23,000 high-quality, textured 3D models annotated with fine-grained, hierarchical part labels across 50 categories. We benchmark PartNeXt on two tasks: (1) class-agnostic part segmentation, where state-of-the-art methods (e.g., PartField, SAMPart3D) struggle with fine-grained and leaf-level parts, and (2) 3D part-centric question answering, a new benchmark for 3D-LLMs that reveals significant gaps in open-vocabulary part grounding. Additionally, training Point-SAM on PartNeXt yields substantial gains over PartNet, underscoring the dataset's superior quality and diversity. By combining scalable annotation, texture-aware labels, and multi-task evaluation, PartNeXt opens new avenues for research in structured 3D understanding.
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。