GaussianDreamerPro: Text to Manipulable 3D Gaussians with Highly Enhanced Quality

TL;DR

GaussianDreamerPro introduces a novel framework that enhances the quality of text-to-3D Gaussian asset generation by binding Gaussians to evolving geometry, resulting in highly detailed and manipulable 3D assets.

Contribution

It proposes a new method to control Gaussian growth during generation by binding them to geometry, significantly improving quality over previous approaches.

Findings

Generated assets show significantly enhanced details and quality.

Assets can be seamlessly integrated into downstream manipulation pipelines.

The framework enables progressive enrichment of geometry and appearance.

Abstract

Recently, 3D Gaussian splatting (3D-GS) has achieved great success in reconstructing and rendering real-world scenes. To transfer the high rendering quality to generation tasks, a series of research works attempt to generate 3D-Gaussian assets from text. However, the generated assets have not achieved the same quality as those in reconstruction tasks. We observe that Gaussians tend to grow without control as the generation process may cause indeterminacy. Aiming at highly enhancing the generation quality, we propose a novel framework named GaussianDreamerPro. The main idea is to bind Gaussians to reasonable geometry, which evolves over the whole generation process. Along different stages of our framework, both the geometry and appearance can be enriched progressively. The final output asset is constructed with 3D Gaussians bound to mesh, which shows significantly enhanced details and quality compared with previous methods. Notably, the generated asset can also be seamlessly integrated into downstream manipulation pipelines, e.g. animation, composition, and simulation etc., greatly promoting its potential in wide applications. Demos are available at https://taoranyi.com/gaussiandreamerpro/.