ATT3D: Amortized Text-to-3D Object Synthesis

Autor:	Lorraine, Jonathan, Xie, Kevin, Zeng, Xiaohui, Lin, Chen-Hsuan, Takikawa, Towaki, Sharp, Nicholas, Lin, Tsung-Yi, Liu, Ming-Yu, Fidler, Sanja, Lucas, James
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence Computer Science - Computer Vision and Pattern Recognition 68T45 I.2.6 I.2.7 I.3.6 I.3.7
Druh dokumentu:	Working Paper
Popis:	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
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2306.07349 Zobrazit plný text záznamu View this record from Arxiv