Vision-CAIR/3DCoMPaT-v2

3DCoMPaT++: An improved large-scale 3D vision dataset for compositional recognition

38
/ 100
Emerging

This dataset offers 16 million rendered views of over 10 million stylized 3D shapes, carefully annotated with part details, alongside matching RGB point clouds, 3D textured meshes, depth maps, and segmentation masks. It helps researchers and engineers who are developing computer vision models that need to understand 3D objects and their components in detail. The dataset provides structured 3D object data and corresponding 2D images for training and evaluating these models.

No commits in the last 6 months.

Use this if you are a computer vision researcher or engineer building or evaluating advanced models for 3D object recognition, part segmentation, or material composition.

Not ideal if you are looking for a simple dataset for basic 2D image classification or if your models do not require detailed 3D part-instance level annotations.

3D computer vision object recognition part segmentation material classification robotics vision
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

96

Forks

8

Language

Python

License

BSD-3-Clause

Last pushed

Oct 14, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Vision-CAIR/3DCoMPaT-v2"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.