English

Elevating 3D Models: High-Quality Texture and Geometry Refinement from a Low-Quality Model

Graphics 2025-07-16 v1 Computer Vision and Pattern Recognition

Abstract

High-quality 3D assets are essential for various applications in computer graphics and 3D vision but remain scarce due to significant acquisition costs. To address this shortage, we introduce Elevate3D, a novel framework that transforms readily accessible low-quality 3D assets into higher quality. At the core of Elevate3D is HFS-SDEdit, a specialized texture enhancement method that significantly improves texture quality while preserving the appearance and geometry while fixing its degradations. Furthermore, Elevate3D operates in a view-by-view manner, alternating between texture and geometry refinement. Unlike previous methods that have largely overlooked geometry refinement, our framework leverages geometric cues from images refined with HFS-SDEdit by employing state-of-the-art monocular geometry predictors. This approach ensures detailed and accurate geometry that aligns seamlessly with the enhanced texture. Elevate3D outperforms recent competitors by achieving state-of-the-art quality in 3D model refinement, effectively addressing the scarcity of high-quality open-source 3D assets.

Keywords

Cite

@article{arxiv.2507.11465,
  title  = {Elevating 3D Models: High-Quality Texture and Geometry Refinement from a Low-Quality Model},
  author = {Nuri Ryu and Jiyun Won and Jooeun Son and Minsu Gong and Joo-Haeng Lee and Sunghyun Cho},
  journal= {arXiv preprint arXiv:2507.11465},
  year   = {2025}
}

Comments

Accepted to SIGGRAPH 2025. For the project page, see https://cg.postech.ac.kr/research/Elevate3D/

R2 v1 2026-07-01T04:02:40.319Z