Back to Search
Start Over
ATT3D: Amortized Text-to-3D Object Synthesis
- Publication Year :
- 2023
-
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.<br />Comment: 22 pages, 20 figures
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2306.07349
- Document Type :
- Working Paper