1. ATT3D: Amortized Text-to-3D Object Synthesis
- Author
-
Lorraine, Jonathan, Xie, Kevin, Zeng, Xiaohui, Lin, Chen-Hsuan, Takikawa, Towaki, Sharp, Nicholas, Lin, Tsung-Yi, Liu, Ming-Yu, Fidler, Sanja, and Lucas, James
- Subjects
FOS: Computer and information sciences ,I.2.6 ,I.2.7 ,I.3.6 ,I.3.7 ,Computer Science - Machine Learning ,Artificial Intelligence (cs.AI) ,Computer Science - Artificial Intelligence ,Computer Vision and Pattern Recognition (cs.CV) ,Computer Science - Computer Vision and Pattern Recognition ,68T45 ,Machine Learning (cs.LG) - Abstract
Text-to-3D modelling 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 knowledge-sharing between prompts to generalize to unseen setups and smooth interpolations between text for novel assets and simple animations., Comment: 22 pages, 20 figures
- Published
- 2023
- Full Text
- View/download PDF