# PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding

## TL;DR

PartNet introduces a comprehensive large-scale 3D object dataset with detailed hierarchical part annotations, enabling advanced benchmarking and development of 3D part recognition algorithms.

## Contribution

The paper provides a new extensive dataset with hierarchical part annotations and establishes benchmark tasks for 3D part recognition, along with a novel segmentation method.

## Key findings

- Benchmarking of state-of-the-art algorithms on new dataset
- Proposed method outperforms existing approaches
- Dataset supports diverse 3D shape analysis tasks

## Abstract

We present PartNet: a consistent, large-scale dataset of 3D objects annotated with fine-grained, instance-level, and hierarchical 3D part information. Our dataset consists of 573,585 part instances over 26,671 3D models covering 24 object categories. This dataset enables and serves as a catalyst for many tasks such as shape analysis, dynamic 3D scene modeling and simulation, affordance analysis, and others. Using our dataset, we establish three benchmarking tasks for evaluating 3D part recognition: fine-grained semantic segmentation, hierarchical semantic segmentation, and instance segmentation. We benchmark four state-of-the-art 3D deep learning algorithms for fine-grained semantic segmentation and three baseline methods for hierarchical semantic segmentation. We also propose a novel method for part instance segmentation and demonstrate its superior performance over existing methods.