# facebookresearch/uco3d

Uncommon Objects in 3D dataset

Repository: https://github.com/facebookresearch/uco3d
Canonical: https://ross.abutalabs.com/products/uco3d
Language: Python
License: CC-BY-4.0
License Family: other
Last push: 2025-11-13T15:19:38+00:00

## Health v2 (maintenance only)
Score: 45/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 52, release rhythm 35, longevity 45
- inputs: {"age_days": 638, "days_push": 293, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1343, forks 186 (observed 2026-08-28T04:04:26.368738+00:00)

## What it is
uCO3D (UnCommon Objects in 3D) is a large-scale dataset from Meta AI containing ~170,000 turn-table videos of objects from ~1000 LVIS categories, annotated with segmentation, camera poses, point clouds, 3D Gaussian Splats, and captions. This repository provides download scripts and tooling for working with the dataset, which is hosted on Hugging Face.

## Use cases
- download a large-scale 3D object video dataset
- train 3D reconstruction or novel view synthesis models
- get camera poses and point clouds for object videos
- obtain 3D Gaussian Splat reconstructions of real objects
- find multi-category 3D object data with captions
- preview a small subset before committing to a 19 TB download

## When to choose
- you need large-scale real-world 3D object data for training generative or reconstruction models
- you want videos with rich annotations like segmentation, poses, and Gaussian Splats
- you need diverse object categories from the LVIS taxonomy with text captions

## When to avoid
- you lack ~19.3 TB of storage for the full dataset
- you only need synthetic 3D data or meshes rather than real captured videos
- you need frame-based data like CO3Dv2 instead of full videos

## Facets
- artifact type: dataset
- maturity: stable
- function: data-science, machine-learning, computer-vision, image-processing, video-processing
- domain: computer-vision, machine-learning, artificial-intelligence
- platform: python, windows
- tags: 3d-dataset, 3d-reconstruction, gaussian-splatting, camera-pose, point-clouds, lvis, video-dataset, facebook-research, cc-by-4.0, datasets, linux, macos

## Member repositories
- facebookresearch/uco3d (main) score 45

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:26.368738+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:42:53.880747+00:00, confidence not recorded.
  - readme: https://github.com/facebookresearch/uco3d (fetched 2026-08-28T04:04:26.368738+00:00, sha e6c2bc5c933b)
- Data as of 2026-08-30T08:39:29.467469+00:00.