PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding

TL;DR

PartNeXt is a comprehensive, textured 3D dataset with hierarchical part annotations, designed to advance fine-grained 3D part understanding and benchmark new tasks like part segmentation and question answering.

Contribution

It introduces a large-scale, textured 3D dataset with hierarchical labels, addressing limitations of prior datasets and enabling new research in 3D understanding and language tasks.

Findings

State-of-the-art methods struggle with fine-grained, leaf-level parts.

Training Point-SAM on PartNeXt improves performance over PartNet.

PartNeXt enables new benchmarks for 3D part segmentation and question answering.

Abstract

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.