SVG-Head: Hybrid Surface-Volumetric Gaussians for High-Fidelity Head Reconstruction and Real-Time Editing
Heyi Sun, Cong Wang, Tian-Xing Xu, Jingwei Huang, Di Kang, Chunchao Guo, Song-Hai Zhang

TL;DR
SVG-Head introduces a hybrid surface-volumetric Gaussian representation for high-fidelity, editable head avatars that enable real-time appearance editing and improved reconstruction quality in AR/VR applications.
Contribution
It proposes a novel hybrid Gaussian model with mesh-aware UV mapping for explicit texture editing and enhanced head reconstruction.
Findings
High-fidelity rendering results on NeRSemble dataset
First method to support explicit texture images for Gaussian head avatars
Enables real-time appearance editing
Abstract
Creating high-fidelity and editable head avatars is a pivotal challenge in computer vision and graphics, boosting many AR/VR applications. While recent advancements have achieved photorealistic renderings and plausible animation, head editing, especially real-time appearance editing, remains challenging due to the implicit representation and entangled modeling of the geometry and global appearance. To address this, we propose Surface-Volumetric Gaussian Head Avatar (SVG-Head), a novel hybrid representation that explicitly models the geometry with 3D Gaussians bound on a FLAME mesh and leverages disentangled texture images to capture the global appearance. Technically, it contains two types of Gaussians, in which surface Gaussians explicitly model the appearance of head avatars using learnable texture images, facilitating real-time texture editing, while volumetric Gaussians enhance the…
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.
