1. [Publications](/index.php/publications)
2. ATT3D: Amortized Text-To-3D Object Synthesis
 
 # ATT3D: Amortized Text-To-3D Object Synthesis

  ![](/sites/default/files/styles/wide/public/publications/Teaser_0.png?itok=xW_ntp3N)

 Text-to-3D modeling has seen exciting progress by combining generative text-to-image models with image-to-3D methods like Neural Radiance Fields. DreamFusion recently achieved high-quality results but requires a lengthy, per-prompt optimization to create 3D objects. To address this, we amortize optimization over text prompts by training on many prompts simultaneously with a unified model, instead of separately. With this, we share computation across a prompt set, training in less time than per-prompt optimization. Our framework - Amortized Text-to-3D (ATT3D) - enables sharing of knowledge between prompts to generalize to unseen setups and smooth interpolations between text for novel assets and simple animations.



 ## Authors



Jonathan Lorraine (NVIDIA)

Kevin Xie (NVIDIA)

Xiaohui Zeng (NVIDIA)

[Chen-Hsuan Lin](/index.php/person/chen-hsuan-lin)

Towaki Takikawa (NVIDIA)

Nicholas Sharp (NVIDIA)

[Tsung-Yi Lin](/index.php/person/tsung-yi-lin)

[Ming-Yu Liu](/index.php/person/ming-yu-liu)

Sanja Fidler (NVIDIA)

James Lucas (NVIDIA)

 

 

 ## Publication Date



Monday, October 2, 2023

 

 ## Published in



[ICCV](https://openaccess.thecvf.com/content/ICCV2023/papers/Lorraine_ATT3D_Amortized_Text-to-3D_Object_Synthesis_ICCV_2023_paper.pdf)

 

 ## Research Area



[Artificial Intelligence and Machine Learning ](/index.php/research-area/machine-learning-artificial-intelligence)

[Computer Vision](/index.php/research-area/computer-vision)

[Generative AI](/index.php/research-area/generative-ai)

 

 

 ## External Links



[Project Page](https://research.nvidia.com/labs/toronto-ai/ATT3D/)

[Paper](https://arxiv.org/abs//2306.07349)