Fast Texture Transfer for XR Avatars via Barycentric UV Conversion
Hail Song, Seokhwan Yang, Woontack Woo

TL;DR
This paper introduces a rapid and artifact-free texture transfer method for XR avatars using barycentric UV conversion, significantly enhancing speed and quality over traditional approaches.
Contribution
It proposes a novel barycentric UV conversion technique that precomputes UV mappings into a single matrix for ultra-fast texture transfer on full-body avatars.
Findings
Speedup of over 7000x compared to baseline
Elimination of boundary artifacts in textures
Improved texture quality and transfer efficiency
Abstract
We present a fast and efficient method for transferring facial textures onto SMPL-X-based full-body avatars. Unlike conventional affine-transform methods that are slow and prone to visual artifacts, our method utilizes a barycentric UV conversion technique. Our approach precomputes the entire UV mapping into a single transformation matrix, enabling texture transfer in a single operation. This results in a speedup of over 7000x compared to the baseline, while also significantly improving the final texture quality by eliminating boundary artifacts. Through quantitative and qualitative evaluations, we demonstrate that our method offers a practical solution for personalization in immersive XR applications. The code is available online.
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.
