Elevating 3D Models: High-Quality Texture and Geometry Refinement from a Low-Quality Model
Nuri Ryu, Jiyun Won, Jooeun Son, Minsu Gong, Joo-Haeng Lee, Sunghyun Cho

TL;DR
Elevate3D is a framework that enhances low-quality 3D models by improving textures and geometry through a view-by-view process, leveraging monocular cues for detailed, high-quality assets.
Contribution
The paper introduces Elevate3D, a novel 3D model refinement framework that jointly improves textures and geometry, surpassing previous methods that focused mainly on textures.
Findings
Achieves state-of-the-art quality in 3D model refinement
Effectively enhances textures while fixing geometric degradations
Outperforms recent competitors in 3D asset quality
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
