Skip to main content

Source code of the dataset toolkit for PartNeXt

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

arXiv Project Page 🤗 Hugging Face Dataset

Penghao Wang, Yiyan He, Xin Lv, Yukai Zhou, Lan Xu, Jingyi Yu, Jiayuan Gu†

ShanghaiTech University

Neurips 2025 Dataset and Benchmark Track

| Project Page | Paper | Dataset | Dataset Toolkit | Benchmark code (Soon) | Annotation code (Soon) |

Usage

Please refer to PartNeXt repo for usage of this lib.

Acknowledgement

Our PartNeXt dataset is based on Objaverse, ABO, 3D-Future, thanks for these awesome datasets. If there is any license issue, please contact us and we will remove the data.

Thanks for Benyuan AI data for data annotation.

If you find our dataset useful in your research, please consider citing our paper.

BibTex Coming Soon

Metadata

Release files for partnext 1.0.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for partnext 1.0.1
File Size Uploaded
partnext-1.0.1.tar.gz 5.1 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for partnext 1.0.1
File Interpreter ABI Platform
partnext-1.0.1-py3-none-any.whl Python 3 none any Details

Total release size: 11.1 kB

Release files / partnext-1.0.1.tar.gz

Download URL partnext-1.0.1.tar.gz
Size 5.1 kB
Tags Source
SHA-256 checksum
How to use checksums
6ce5a7408c99aa1a6df49d7293a47bfcd60153434d6fbf95e7dfa2b96ab012d6
BLAKE2b-256 checksum
How to use checksums
3f1e8c561e85a757366033fce17ce05957b7be9b522f2ab69cac0b3e4f70a850
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.11.13

Release files / partnext-1.0.1-py3-none-any.whl

Download URL partnext-1.0.1-py3-none-any.whl
Size 6.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
337e39aeef553b9bfecf407387ce58943f031b105884561bc39f260b0c101e55
BLAKE2b-256 checksum
How to use checksums
bf118cf81d00c7a9a22b86b77a43f57973ece3ed3b0f62ed8627a2149cc30e38
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.11.13

Release history Release notifications | RSS feed

This release

1.0.1 This release

2 release files

1.0.0

2 release files

0.0.1

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page