Dual3D: Efficient and Consistent Text-to-3D Generation with Dual-mode Multi-view Latent Diffusion

TL;DR

Dual3D introduces a dual-mode latent diffusion framework for rapid, high-quality text-to-3D asset generation, leveraging pre-trained models and a toggling inference strategy to achieve 10-second generation times.

Contribution

It proposes a novel dual-mode multi-view latent diffusion model with a toggling inference strategy, enabling fast and consistent text-to-3D generation from pre-trained models.

Findings

Generates 3D assets in 10 seconds with high quality

Achieves state-of-the-art performance in text-to-3D tasks

Reduces inference steps by a factor of 10 without quality loss

Abstract

We present Dual3D, a novel text-to-3D generation framework that generates high-quality 3D assets from texts in only $1$ minute.The key component is a dual-mode multi-view latent diffusion model. Given the noisy multi-view latents, the 2D mode can efficiently denoise them with a single latent denoising network, while the 3D mode can generate a tri-plane neural surface for consistent rendering-based denoising. Most modules for both modes are tuned from a pre-trained text-to-image latent diffusion model to circumvent the expensive cost of training from scratch. To overcome the high rendering cost during inference, we propose the dual-mode toggling inference strategy to use only $1/10$ denoising steps with 3D mode, successfully generating a 3D asset in just $10$ seconds without sacrificing quality. The texture of the 3D asset can be further enhanced by our efficient texture refinement process in a short time. Extensive experiments demonstrate that our method delivers state-of-the-art performance while significantly reducing generation time. Our project page is available at https://dual3d.github.io