PartNeXt：面向细粒度和层次化3D部件理解的下一代数据集
PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding
AI总结：
PartNeXt通过23000个高质量纹理3D模型，解决传统数据集在可扩展性和实用性上的不足，提升细粒度部件分割和3D部件问答任务的性能。
摘要：
理解物体的构成部件对于推动计算机视觉、图形学和机器人学发展至关重要。尽管PartNet等数据集推动了3D部件理解的进步，但其依赖于无纹理几何体和专家依赖的标注限制了可扩展性和实用性。我们引入PartNeXt，一个新一代数据集，通过超过23000个高质量、纹理化的3D模型，标注了50个类别中的细粒度、层次化部件标签。我们在此基础上进行了两项任务的基准测试：（1）无类别部件分割，其中最先进的方法（如PartField、SAMPart3D）在细粒度和叶级别部件上表现不佳；（2）3D部件中心问答，一个新的用于3D-LLMs的基准测试，揭示了开放词汇部件定位中的显著差距。此外，使用PartNeXt训练Point-SAM相较于PartNet有显著提升，凸显了该数据集的优越质量和多样性。通过结合可扩展的标注、纹理感知标签和多任务评估，PartNeXt为结构化3D理解的研究开辟了新途径。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
