GradeADreamer: Enhanced Text-to-3D Generation Using Gaussian Splatting and Multi-View Diffusion

TL;DR

GradeADreamer introduces a three-stage pipeline for efficient, high-quality text-to-3D asset generation that reduces time and mitigates common multi-face issues using Gaussian splats and multi-view diffusion.

Contribution

It presents a novel three-stage training pipeline utilizing Gaussian splats and multi-view diffusion to improve quality and speed in text-to-3D generation.

Findings

Achieves high-quality 3D assets in under 30 minutes on a single GPU.

Significantly reduces the Multi-face Janus problem.

Outperforms previous methods in user preference rankings.

Abstract

Text-to-3D generation has shown promising results, yet common challenges such as the Multi-face Janus problem and extended generation time for high-quality assets. In this paper, we address these issues by introducing a novel three-stage training pipeline called GradeADreamer. This pipeline is capable of producing high-quality assets with a total generation time of under 30 minutes using only a single RTX 3090 GPU. Our proposed method employs a Multi-view Diffusion Model, MVDream, to generate Gaussian Splats as a prior, followed by refining geometry and texture using StableDiffusion. Experimental results demonstrate that our approach significantly mitigates the Multi-face Janus problem and achieves the highest average user preference ranking compared to previous state-of-the-art methods. The project code is available at https://github.com/trapoom555/GradeADreamer.