Datasets › PartNet

PartNet

Introduced by Kaichun Mo et al. in PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding archive 2025-07-28

PartNet is a consistent, large-scale dataset of 3D objects annotated with fine-grained, instance-level, and hierarchical 3D part information. The 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.

Source: PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding Image Source: https://cs.stanford.edu/~kaichun/partnet/

Homepage Benchmarks Papers JSON

Benchmarks archive 2025-07-28

All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

		First row (archive order)	Paper	Code
3D Semantic Segmentation	PartNet	CSN mIOU 62.1	Cross-Shape Attention for Part Segmentation of 3D Point Clouds	marios2019/CSN	6	Compare
3D Instance Segmentation	PartNet	Semantic Segmentation-Assisted Instance Feature Fusion mAP50 64.1	Semantic Segmentation-Assisted Instance Feature Fusion...	isunchy/3d_instance_segmentation	3	Compare
Instance Segmentation	PartNet	PE mAP50 57.5	Point Cloud Instance Segmentation using Probabilistic Embeddings	—	1	Compare

Papers archive 2025-07-28

8 shown of 8 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 156. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

			Date	Samples run Syntology
Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level 3D Part Instance Segmentation	1	1	9 Aug 2022	ran 2 of 3 samples (1 unverified)
FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling	1	1	17 Dec 2020	not harvested
Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discrimination	1	1	3 Aug 2020	ran 0 of 9 samples (9 unverified)
A Closer Look at Local Aggregation Operators in Point Cloud Analysis	1	1	2 Jul 2020	ran 0 of 9 samples (9 unverified; 9 pointer-only for licence)
Cross-Shape Attention for Part Segmentation of 3D Point Clouds	1	1	20 Mar 2020	not harvested
Point Cloud Instance Segmentation using Probabilistic Embeddings	0	2	30 Nov 2019	not harvested
DeepGCNs: Making GCNs Go as Deep as CNNs	4	1	15 Oct 2019	ran 1 of 9 samples (8 unverified; 1 pointer-only for licence)
PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding	5	2	6 Dec 2018	not harvested

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

Semantic Segmentation Instance Segmentation 3D Semantic Segmentation 3D Instance Segmentation

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

PartNet

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections