DreamMapping: High-Fidelity Text-to-3D Generation via Variational Distribution Mapping

TL;DR

This paper introduces Variational Distribution Mapping (VDM) and Distribution Coefficient Annealing (DCA) to improve text-to-3D generation, achieving higher fidelity and efficiency by refining score distillation sampling techniques.

Contribution

The paper proposes VDM and DCA to enhance score distillation sampling for text-to-3D generation, enabling faster training and higher quality outputs.

Findings

VDM accelerates distribution modeling by skipping Jacobian calculations.

DCA improves distillation precision through timestep-dependent annealing.

Experiments show high-fidelity, realistic 3D assets with efficient optimization.

Abstract

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.