Logo Logo
deutsch
directory schraeg
Knowledge
Codecs
Hardware
Camcorders· Cinema-Kamera· Computers· Drohnen· GPU· Kamera-Zubehör· Video-DSLR· accessories
Software
Compositing· Color correction· DV Editing
DV-Movies

HowTo
Shooting· Sound
Misc
Forschung· Reviews· Streaming
/// News
DreamFusion: New Google AI generates 3D models by text description only

DreamFusion: New Google AI generates 3D models by text description only

[10:14 Tue,11.October 2022   by ]    

After the generation of arbitrary images and videos by means of a simple text description, now comes another logical development step - the generation of arbitrary 3D models. The new method developed by Google and christened "DreamFusion" is also based on a pre-trained 2D text-image diffusion model (such as Google&s Imagen or Stable Diffusion) and generates 3D objects after description, which can be viewed from any angle, re-lit by any illumination or integrated into any 3D environment.



Implicitly, even with the 2D images of, for example, Stable Diffusion, it was clear that the AI had only developed some sort of understanding of three-dimensional space and the objects within it through training with billions of images - via DreamFusion, this knowledge can now be used to selectively create individual 3D objects. DreamFusion&s approach therefore requires no explicit 3D training data and no changes to the image diffusion model. The generated NeRF (Neural Radiance Field) models can be exported via Marching Cubes algorithm into 3D meshes, which can then be easily used in 3D renderers or modeling software.

DreamFusion-3D-Examples
DreamFusion


DreamFusion can not only generate any simple object, but it can also perform an action and combine it with another object (such as "a ghost eating a hamburger") or, for example, wearing a certain clothing ("a chimpanzee dressed like Henry VIII, King of England").

As with the image generation AIs, multiple results can be generated using a prompt - moreover, the algorithm can easily be extended to generate multiple 3D models simultaneously. There is already an official online gallery with hundreds of 3D models generated by dreamFusion.

DreamFusion-3D-SW
DreamFusion


The chance to create so easily complex 3D-models of arbitrary objects will open or simplify many application possibilities. The next logical step is then the simple animation of these models or even the specific modification.

DreamFusion-3D-Paar-Examples
DreamFusion


Unfortunately, Google has not published the code for DreamFusion or provided public access to the model with the possibility for users to generate 3D models themselves, but developers have already started to implement the idea behind DreamFusion via stable diffusion as an open project called Stable-Dreamfusion.

Link more infos at bei dreamfusion3d.github.io

deutsche Version dieser Seite: DreamFusion: Neue Google KI generiert beliebige 3D Modelle - nur per Textbeschreibung

  

  Vorige News lesen Nächste News lesen 
bildDJI Store Day: bis zu 40% Rabatt und Geschenke bildNvidia RTX 4090 Nachfolger bringt Netzteile zum Schmelzen?


related news:1E0Nvidia Magic3D - create any 3D object by text description 29.November 2022
AvatarCLIP: New AI generates and animates 3D avatars by text description 28.October 2022
Luma AI: New smartphone app creates 3D models of any object 21.October 2022
Nvidia creates editable 3D model from photos of an object 24.June 2022
The 35mm film camera from the 3D printer 20.May 2022
Nvidia Instant NeRF - 3D scene from 2D images in record time 28.March 2022
Four new analog 65mm IMAX film cameras in development 21.March 2022
alle Newsmeldungen zum Thema 3D
1E0Heavy Metal meets Midjourney: Music video made from 10,000 AI-generated images 4.December 2022
Meta Encodec uses AI to compress audio files significantly more than MP3 21.November 2022
AI copies movie style of "Into the Spider-Verse" in record time 14.November 2022
MAXIM - AI tool combines various image enhancements in one model 13.November 2022
Blackmagic DaVinci Resolve 18.1 Update - with AI voice isolation 11.November 2022
Photostock portal Shutterstock gives an answer to the big question and integrates AI images 5.November 2022
AvatarCLIP: New AI generates and animates 3D avatars by text description 28.October 2022
alle Newsmeldungen zum Thema Machine Learning


[nach oben]
















Archiv Newsmeldungen

2022

December - November - October - September - August - July - June - May - April - March - February - January

2021
December - November - October - September - August - July - June - May - April - March - February - January

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

2003

2002

2001

2000






































deutsche Version dieser Seite: DreamFusion: Neue Google KI generiert beliebige 3D Modelle - nur per Textbeschreibung



last update : 6.Dezember 2022 - 18:02 - slashCAM is a project by channelunit GmbH- mail : slashcam@--antispam:7465--slashcam.de - deutsche Version