openai/point-e
OpenAI's diffusion system for generating 3D point clouds from text and image prompts.
Not currently ranked — collecting fresh signals.
star history
Point-E is OpenAI’s official implementation of a 3D point cloud synthesis system using diffusion models. It generates 3D point clouds directly from text descriptions or from synthetic view images. The release includes a text-to-3D model, an image-conditioned point cloud generator, and an SDF regression model for converting point clouds into meshes. It also provides evaluation scripts using P-FID and P-IS metrics for assessing generation quality.
Frequently asked
- What is openai/point-e?
- OpenAI's diffusion system for generating 3D point clouds from text and image prompts.
- Is point-e open source?
- Yes — openai/point-e is open source, released under the MIT license.
- What language is point-e written in?
- openai/point-e is primarily written in Python.
- How popular is point-e?
- openai/point-e has 6.9k stars on GitHub.
- Where can I find point-e?
- openai/point-e is on GitHub at https://github.com/openai/point-e.