PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding
This addresses the problem of scalable and high-quality 3D part understanding for computer vision and robotics researchers, though it is incremental as it builds on prior datasets like PartNet.
The paper tackles the limitations of existing 3D part understanding datasets by introducing PartNeXt, a dataset with over 23,000 textured 3D models and fine-grained annotations, which improves part segmentation and enables new benchmarks like 3D part-centric question answering, showing substantial gains in training models.
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.