GaussianDreamerPro: Text to Manipulable 3D Gaussians with Highly Enhanced Quality
This work addresses the quality gap in text-to-3D generation for applications in animation and simulation, representing an incremental improvement over prior methods.
The paper tackles the problem of generating low-quality 3D Gaussian assets from text by proposing GaussianDreamerPro, which binds Gaussians to evolving geometry to enhance details, resulting in significantly improved quality and manipulable outputs for applications like animation.
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/.