pith. sign in

arxiv: 2409.05099 · v4 · pith:NC4MXTMVnew · submitted 2024-09-08 · 💻 cs.CV · cs.GR

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

classification 💻 cs.CV cs.GR
keywords distributiongenerationtext-to-3dvariationaldesigndistillinghigh-fidelityimages
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. CAdam: Context-Adaptive Moment Estimation for 3D Gaussian Densification in Generative Distillation

    cs.LG 2026-05 unverdicted novelty 7.0

    CAdam reinterprets densification in generative 3DGS as signal verification via gradient-moment interference, quantile context, and SNR gating to achieve large reductions in primitive count with comparable quality.

  2. OmniFit: Multi-modal 3D Body Fitting via Scale-agnostic Dense Landmark Prediction

    cs.CV 2026-04 unverdicted novelty 7.0

    OmniFit uses a conditional transformer decoder to predict dense body landmarks from multi-modal inputs for scale-agnostic SMPL-X fitting, outperforming prior methods by 57-81% and reaching millimeter accuracy on CAPE ...

  3. GaussiAnimate: Reconstruct and Rig Animatable Categories with Level of Dynamics

    cs.CV 2026-04 unverdicted novelty 6.0

    Skelebones compresses 4D Gaussian shapes into compact, controllable bones and skeletons, delivering 17.3% PSNR gains over LBS and 21.7% over BoB for unseen poses while preserving reconstruction quality.

  4. A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation

    cs.CV 2025-08 unverdicted novelty 3.0

    A survey that categorizes and summarizes methods applying 3D Gaussian Splatting to segmentation, editing, generation, and related tasks, including datasets and evaluation protocols.