DreamMapping: High-Fidelity Text-to-3D Generation via Variational Distribution Mapping
This work addresses quality issues in text-to-3D generation for content creation, representing an incremental improvement over existing SDS-based methods.
The paper tackles the problem of over-saturated color and excess smoothness in text-to-3D generation using Score Distillation Sampling (SDS), and introduces Variational Distribution Mapping (VDM) and Distribution Coefficient Annealing (DCA) to improve fidelity and efficiency, achieving high-fidelity and realistic 3D assets with optimization efficiency as demonstrated in experiments.
Score Distillation Sampling (SDS) has emerged as a prevalent technique for text-to-3D generation, enabling 3D content creation by distilling view-dependent information from text-to-2D guidance. However, they frequently exhibit shortcomings such as over-saturated color and excess smoothness. In this paper, we conduct a thorough analysis of SDS and refine its formulation, finding that the core design is to model the distribution of rendered images. Following this insight, we introduce a novel strategy called Variational Distribution Mapping (VDM), which expedites the distribution modeling process by regarding the rendered images as instances of degradation from diffusion-based generation. This special design enables the efficient training of variational distribution by skipping the calculations of the Jacobians in the diffusion U-Net. We also introduce timestep-dependent Distribution Coefficient Annealing (DCA) to further improve distilling precision. Leveraging VDM and DCA, we use Gaussian Splatting as the 3D representation and build a text-to-3D generation framework. Extensive experiments and evaluations demonstrate the capability of VDM and DCA to generate high-fidelity and realistic assets with optimization efficiency.