# openai/point-e

Point cloud diffusion for 3D model synthesis

Repository: https://github.com/openai/point-e
Canonical: https://ross.abutalabs.com/products/point-e
Language: Python
License: MIT
License Family: permissive
Last push: 2024-07-04T19:05:34+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 97
- inputs: {"age_days": 1366, "days_push": 790, "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 6895, forks 792 (observed 2026-08-28T04:09:51.171068+00:00)

## What it is
Point-E is OpenAI's official release of models and code for generating 3D point clouds from text prompts or images using diffusion models. It also includes an SDF regression model for converting point clouds into meshes, plus evaluation and rendering scripts.

## Use cases
- generate 3D point clouds from text descriptions
- create 3D models from images
- convert point clouds to 3D meshes
- evaluate generated point clouds with P-FID and P-IS metrics
- render 3D point clouds in Blender

## When to choose
- you need to synthesize 3D point clouds from text or image prompts
- you want to experiment with diffusion-based 3D generation research
- you need a pipeline from point clouds to meshes

## When to avoid
- you need production-quality, watertight 3D meshes rather than point clouds
- you want a polished end-user application rather than research code
- you lack a GPU, since sampling is computationally expensive

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, graphics
- domain: artificial-intelligence, deep-learning, graphics, machine-learning
- platform: python
- tags: 3d-generation, point-clouds, diffusion-models, text-to-3d, generative-models, mesh-generation, gpu

## Member repositories
- openai/point-e (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:51.171068+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 2026-08-29T17:41:38.329456+00:00, confidence not recorded.
  - readme: https://github.com/openai/point-e (fetched 2026-08-28T04:09:51.171068+00:00, sha 30cc31e86202)
- Data as of 2026-08-30T08:39:29.467469+00:00.