The number of artificial intelligences that transform written communication into visual arts is increasing. Finally, Google introduced Dreamfusion, the artificial intelligence that transforms written sentences into three-dimensional objects.
Especially DALL-E, which has been opened to everyone’s access recently, midjourneyBy using many different artificial intelligence applications such as , GauGAN2, Craiyon, it was possible to paint and create digital images with our words. A new artificial intelligence to serve in this field was announced by Google today. The name of this artificial intelligence is Dreamfusion.
Late last year, Google released various objects capable of three-dimensional artificial intelligence announced Dream Fields. Dreamfusion, on the other hand, emerged with the combination of this artificial intelligence and Imagen, the image model artificial intelligence of Google.
Producing three-dimensional objects from two-dimensional images
“We are pleased to announce DreamFusion, our new method for Text-to-3D!
We optimized a NeRF from scratch using a pre-trained text-to-image propagation model. No need for 3D data!”
Neural Radiance Field (NeRF) Thanks to the technology called Imagen, Google’s AI creates a three-dimensional model by combining the two-dimensional images it has. Thus, it is not necessary to train artificial intelligence on three-dimensional models. In addition, the produced models can be used together.
At least for now, the images Google offers are as good as some DALL-E images. not realistic. The points where the technology giant is currently highlighting the product “re-illuminated with Lambertian lighting patterns, with consistent, high-quality normals, surface geometry and depth” able to create. To put it more simply, when you create an image, it is important to consider points such as width-length, front-back, depth. realistic and consistent It is possible to create images.
of Dreamfusion when will it be available There has been no explanation yet, but alternative ideas have already begun to emerge on how it can be used in the future. It seems that this artificial intelligence can be used in many different areas, from images taken in the medical field to fully modeling the structure of the organ to be operated on, to creating models for indie game developers.
Source :
https://mixed-news.com/en/dreamfusion-google-ai-creates-3d-models-from-text/