PlacidDreamer: Advancing Harmony in Text-to-3D Generation

TL;DR

PlacidDreamer introduces a unified text-to-3D generation framework that harmonizes multi-view and text-conditioned generation using a single diffusion model, and employs a novel score distillation method to balance detail richness and saturation.

Contribution

It proposes the Latent-Plane module for unified multi-view diffusion and a Balanced Score Distillation algorithm to address saturation issues in text-to-3D generation.

Findings

Outperforms previous methods in generating diverse and detailed 3D assets.

Effectively balances detail richness and saturation in generated 3D models.

Validated through extensive experiments demonstrating superior quality.

Abstract

Recently, text-to-3D generation has attracted significant attention, resulting in notable performance enhancements. Previous methods utilize end-to-end 3D generation models to initialize 3D Gaussians, multi-view diffusion models to enforce multi-view consistency, and text-to-image diffusion models to refine details with score distillation algorithms. However, these methods exhibit two limitations. Firstly, they encounter conflicts in generation directions since different models aim to produce diverse 3D assets. Secondly, the issue of over-saturation in score distillation has not been thoroughly investigated and solved. To address these limitations, we propose PlacidDreamer, a text-to-3D framework that harmonizes initialization, multi-view generation, and text-conditioned generation with a single multi-view diffusion model, while simultaneously employing a novel score distillation algorithm to achieve balanced saturation. To unify the generation direction, we introduce the Latent-Plane module, a training-friendly plug-in extension that enables multi-view diffusion models to provide fast geometry reconstruction for initialization and enhanced multi-view images to personalize the text-to-image diffusion model. To address the over-saturation problem, we propose to view score distillation as a multi-objective optimization problem and introduce the Balanced Score Distillation algorithm, which offers a Pareto Optimal solution that achieves both rich details and balanced saturation. Extensive experiments validate the outstanding capabilities of our PlacidDreamer. The code is available at \url{https://github.com/HansenHuang0823/PlacidDreamer}.