ATT3D: Amortized Text-to-3D Image Generation | NVIDIA Research

Описание: NVIDIA Research Paper

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

For more - visit our project website: https://research.nvidia.com/labs/toro...