whatisgithub

What is point-e?

openai/point-e — explained in plain English

Analysis updated 2026-06-24

★ 6,889PythonAudience · researcherComplexity · 3/5Setup · moderate

In one sentence

An OpenAI research tool that generates 3D point clouds from text descriptions or images, then optionally converts them into standard 3D mesh files for use in 3D software.

Mindmap

mindmap
  root((point-e))
    What it does
      Text to 3D shape
      Image to 3D shape
      Point cloud generation
    Workflow
      Text prompt input
      Image generation step
      Point cloud output
      Optional mesh export
    Tech Stack
      Python
      Jupyter notebooks
    Use Cases
      3D prototyping
      Research baseline
      Asset generation
    Audience
      AI researchers
      3D experimenters
Click or tap to explore — scroll the page freely

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Generate a rough 3D point cloud of an object from a text prompt for a research or prototyping pipeline.

USE CASE 2

Feed a 2D image into Point-E to produce a 3D point cloud approximation of the depicted object.

USE CASE 3

Convert a generated point cloud to a mesh file for import into standard 3D software or a game engine.

What is it built with?

Python

How does it compare?

openai/point-ehhyo/archeryhugapi/hug
Stars6,8896,8866,893
LanguagePythonPythonPython
Setup difficultymoderatemoderateeasy
Complexity3/54/52/5
Audienceresearcherops devopsdeveloper

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

Designed for researchers, install via pip and run the provided Jupyter notebooks. Text-to-3D quality is lower than image-to-3D for complex objects.

So what is it?

Point-E is an AI system from OpenAI that generates 3D shapes from text descriptions or images. Instead of producing a traditional 3D mesh directly, it creates what is called a point cloud: a collection of thousands of colored dots arranged in three-dimensional space that together represent the shape of an object. A separate model can then convert that point cloud into a mesh, which is the format used by most 3D software. The typical workflow starts with a text prompt. The system first generates a 2D image of the described object, then uses that image as a guide to produce the 3D point cloud. There is also a pure text-to-3D path that skips the image step, though the README notes this produces lower quality results and handles only simple categories and colors. The code is released as a Python package and includes Jupyter notebooks (interactive documents that mix code and explanations) to walk through the main use cases: generating a point cloud from an image, generating one from text, and converting a point cloud to a mesh. Evaluation scripts for measuring quality are also included. The repository accompanies a research paper and is intended mainly for researchers and developers who want to experiment with 3D generation. The README is short and does not cover advanced configuration. Installation is done through pip, the standard Python package installer.

Copy-paste prompts

Prompt 1
Using the Point-E Python package, write code that generates a 3D point cloud from the text prompt 'a red office chair' and saves it as a PLY file.
Prompt 2
Walk me through running the Point-E image-to-3D Jupyter notebook, what image format does it expect, and what does the output point cloud look like?
Prompt 3
Using Point-E, generate a point cloud from an image of a mug and then convert it to a 3D mesh, walk me through the full pipeline step by step.
Prompt 4
What are the quality trade-offs between Point-E's text-to-3D path and its image-to-3D path, and when should I use each?

Frequently asked questions

What is point-e?

An OpenAI research tool that generates 3D point clouds from text descriptions or images, then optionally converts them into standard 3D mesh files for use in 3D software.

What language is point-e written in?

Mainly Python. The stack also includes Python.

How hard is point-e to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is point-e for?

Mainly researcher.

Open on GitHub → Ask about another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.

What are similar repos?