# Enter text – and a finished 3D object appears?

10 January 2023 - [Patrick Poti](https://digitalproduction.com/author/patrick-poti/)

Point-E makes it possible to generate 3D objects using text input – in minutes, with manageable graphics performance. A development of the company OpenAI.

Twelve colorful 3D objects including corgi in santa hat, rainbow pumpkin, fountain, traffic cone, and rubber duck.

**In nuce:** The US company **[OpenAI](https://openai.com/?utm_source=digitalproduction.com&utm_medium=referral&utm_campaign=ongoing)**, which researches artificial intelligence, has published Point-E. Point-E can be used to create 3D objects using text input. This is according to a report by journalist Andrew Tarantola, published on the Engadget news service. Point-E works in a similar way to another development from OpenAI: Dall-E, the text-image generator. The difference is that Point-E creates 3D models – Dall-E only creates still images. The background to this: Dall-E is an artificial intelligence that is used to generate images based on text input (these text inputs are also known as prompts in technical jargon). Digital Production last reported **on** Dall-E on **[27 October 2022](https://www.digitalproduction.com/2022/10/27/mit-der-text-to-bild-ki-dall-e-2-in-microsoft-bing-bilder-generieren/)** , when the generator was integrated into the Microsoft Bing internet search engine.

**In toto:** Point-E is used to create 3D point clouds, also based on prompts. While **[DreamFusion](https://dreamfusion3d.github.io/?utm_source=digitalproduction.com&utm_medium=referral&utm_campaign=ongoing) from** Google – as Andrew Tarantola writes – “usually takes several hours to create 3D objects”, Point-E minimises the process to just a few minutes. In addition, Tarantola goes on to say that Point-E should already work properly with just one GPU – instead of, as with DreamFusion, only producing results when several GPUs are used.

**How does Point-E work?** In the scientific paper **[Point-E: A System for Generating 3D Point Clouds from Complex Prompt](https://arxiv.org/pdf/2212.08751.pdf?utm_source=digitalproduction.com&utm_medium=referral&utm_campaign=ongoing)** , the team led by **[Alex Nichol](https://twitter.com/unixpickle?ref_src=twsrc%5Etfw%7Ctwcamp%5Etweetembed%7Ctwterm%5E1578530905546555397%7Ctwgr%5E450f3dfa7bb98c7b60b2749d7a3fc44df94c45e7%7Ctwcon%5Es1_&ref_url=https%3A%2F%2Fblog.aqnichol.com%2F&utm_source=digitalproduction.com&utm_medium=referral&utm_campaign=ongoing)**, researcher at OpenAI, writes that Point-E utilises “a large corpus of (text, image) pairs”. However, Nichol and his team go on to explain that Point-E was trained using a “smaller dataset of (image, 3D) pairs”. The paper also discusses how 3D objects are created with the support of Point-E. The article states that in the case of a text input (e.g. “A cat eats a burrito”), Point-E first generates a synthetic 3D representation of a burrito-eating cat. The image generated in this way is then run through several diffusion models; these models serve as the basis for a 3D RGB point cloud – first for a coarse 1,024-point cloud model, then a finer 4,096-point model.

**Click to continue:** on **[6 September 2022](https://www.digitalproduction.com/2022/09/06/ki-generierte-kunstwerke-mit-stable-diffusion/)** , Digital Production showed how the text-to-image AI Stable Diffusion allows users to create images using text input.

**Source: [engadget.com](https://www.engadget.com/openai-releases-point-e-dall-e-3d-text-modeling-210007892.html?src=rss&utm_source=digitalproduction.com&utm_medium=referral&utm_campaign=ongoing) (** report by **[Andrew Tarantola](https://www.engadget.com/about/editors/andrew-tarantola/?utm_source=digitalproduction.com&utm_medium=referral&utm_campaign=ongoing)**)

#### About the author

Patrick Poti [Patrick Poti](https://digitalproduction.com/author/patrick-poti/)

### Print

### Article details

Published

10 January 2023, 15:55:01 CET (+01:00)

Author

[Patrick Poti](https://digitalproduction.com/author/patrick-poti/)

Reading time

About 2 min

Word count

362

### Tags

- [AI (190)](https://digitalproduction.com/tag/ai/)
- [Artificial Intelligence (190)](https://digitalproduction.com/tag/artificial-intelligence/)
- [Machine Learning (46)](https://digitalproduction.com/tag/machine-learning/)
- [ML (46)](https://digitalproduction.com/tag/ml/)
- [Stability AI (7)](https://digitalproduction.com/tag/stability-ai/)
- [Stable Diffusion (7)](https://digitalproduction.com/tag/stable-diffusion/)

### Permalink

[https://digitalproduction.com/2023/01/10/text-eingeben-und-ein-fertiges-3d-objekt-erscheint/](https://digitalproduction.com/2023/01/10/text-eingeben-und-ein-fertiges-3d-objekt-erscheint/)