There has been much talk lately about artificial intelligence capable of generating images or text, such as Stable Diffusion or ChatGPT, but as we can read in TechCrunch, OpenAI has released a new artificial intelligence capable of generating 3D models.
The mode of operation of this artificial intelligence is not focused on quality, but on efficiency, because although the models it generates are currently worse than those of the best solutions on the market, it is also true that it does it in a fraction of the timesomething that can be important when finding what we want to say to generate a model.
The name of this artificial intelligence is not a coincidence either, and it is that 3D models are not generated in the traditional sense, generating the mesh, butbut initially an image of what we want is generated, to later convert said image into a cloud of three-dimensional points –similar to what a 3D scanner does— and from there convert said cloud into a 3D model.
We can see that the model is far from infallible, but the results that are being seen lately on the artificial intelligence front are spectacular.
End of Article. Tell us something in the Comments!
Jordi Bercial
Avid technology and electronics enthusiast. I tinkered with computer components almost since I could walk. I started working at Geeknetic after winning a contest on their forum for writing hardware articles. Drift, mechanics and photography lover. Do not hesitate and leave a comment on my articles if you have any questions.
