[3DGS] Text-to-3D using Gaussian Splatting / ver. Kor
2025. 4. 7. 01:29
Paper Information
- Title : Text-to-3D using Gaussian Splatting
- Journal : CVPR 2024
- Author : Chen, Zilong, et al
GSGEN: Text-to-3D using Gaussian Splatting
We present Gaussian Splatting based text-to-3D GENeration (Gsgen), the first approach that generates multi-view consistent and delicate 3D assets using 3D Gaussian Splatting. Previous methods suffer from inaccurate geometry and limited fidelity due to the
gsgen3d.github.io
Abstract
Problem :
- inaccurate geometry
- time-consuming
Method : GSGEN - text to 3d model using gaussian
details : Progressive two-stage optimization strategy
- appearance refinement strategy : increasing number of Gaussians
- geometry optimization : coarse representation
=> Generate 3D assets with delicate details and accurate geometry
'Computer Science > AI' 카테고리의 다른 글
